360dialog MCP server
com.360dialog/mcp360dialog.comstreamable-httpv2.2.1Scanned
Manage WhatsApp Business accounts on 360Dialog: channels, templates, sandbox, inbox, and more.
138 tools: 49 can delete or cancel things, 4 do something that can't be undone, 16 change things and 69 only read.
- Reads private data · 22
- Reads text others write · 99
- Can send data out · 13
- 26 findings
Tools listed without sign-in. Remote posture
With Anlyon
49 tools here can delete or cancel things and 4 do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the 360dialog MCP server can do
The 360dialog MCP server is published by 360dialog.com, a domain the MCP Registry verified. It has 138 tools. It can delete or cancel things (49 tools: set_display_name, update_channel_profile, set_business_username, update_commerce_settings and 45 more), do things that cannot be undone, such as sending, paying or publishing (mba_send_agent_event, mba_test_agent, mba_release_thread_control and mba_send_message) and create or change data (16 tools: start_signup, check_number_eligibility, start_number_onboarding, sandbox_complete_registration and 12 more). 69 tools only read.
22 tools read private data (search_client_documentation, get_client_documentation_page, get_messaging_analytics and 19 more); 99 tools bring in text other people can write (search_client_documentation, get_client_documentation_page, get_messaging_analytics and 96 more); 13 tools can send data out of your system (get_client_documentation_page, check_number_eligibility, send_test_webhook_event and 10 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
The fixed checks matched 26 findings (annotation-conflict, long-description and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 2.2.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
138 tools
Deletes or cancels 49Claude Code: deny
block_usersBlock WhatsApp users from messaging a channel.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Block WhatsApp users from messaging a channel. Identify each user by phone number or by BSUID; pass at least one of 'phone_numbers' and 'user_ids'. Only a business can block users who recently messaged it, so some users can fail. The result lists which succeeded and which failed with the reason.
Annotations the server declares
- title: Block users
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
change_user_roleChange the role of an existing user of the account.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Change the role of an existing user of the account. Users cannot change their own role. Client users change users of their own client account, partner users users of the partner account. The user may be prompted by 360Dialog for an OTP code delivered to their email address.
Annotations the server declares
- title: Change user role
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
create_partner_change_requestRequest that the client's numbers move to a new partner.Reads text others writeNo findings
Why it is in this group
- The name "create_partner_change_request" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Request that the client's numbers move to a new partner. The new partner has to approve the request; then the numbers are moved, which changes who manages them and who is billed. ALWAYS call 'preview_partner_change_request' first with the same arguments, show its result to the user and get their confirmation before calling this tool. This tool also runs the preview itself and does NOT create the request when the preview finds issues; it then returns the issues instead. The user may be prompted by 360Dialog for an OTP code delivered to their email address.
Annotations the server declares
- title: Create partner change request
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
create_templateUse this tool to create a WhatsApp message template.1 finding
Why it is in this group
- The name "create_template" says "create": a word for a change.
- The server marks it destructive (destructiveHint: true).
Findings
- Info
The description is 6,449 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "..."body_text": [ ["Alice", "Downtown"] ] } } ] }"
Description, as the server wrote it Use this tool to create a WhatsApp message template. For this tool's 'template_json' property, pass a JSON matching this shape: { "name": string, "language": string, "category": "MARKETING" | "AUTHENTICATION" | "UTILITY", "components": Component[], } General rules: - name must be lowercase snake_case. - category must be uppercase. - language must be a WhatsApp locale code such as "en_US", "tr", "es", "pt_BR". - Only include fields supported by the component variant. - Do not include null fields. - Components should normally be ordered as: 1. header, if any 2. body 3. footer, if any 4. buttons, if any - A template can have at most one header, one body, one footer, and one buttons component. - BODY is required unless the user is clearly creating a special authentication template handled elsewhere. - HEADER and FOOTER are optional. - BUTTONS are optional. Component variants: 1. Text header without variables { "type": "HEADER", "format": "text", "text": "Your order update" } Use this when the header is plain text. 2. Text header with variables { "type": "HEADER", "format": "TEXT", "text": "Hi {{1}}", "example": { "header_text": ["Alice"] } } Rules: - Text header supports template variables. - If text contains variables, include example.header_text. - The example array must contain sample values in the same order as the variables appear. - For named parameters, the placeholder names appear in text, but the examples are still values. 3. Image header { "type": "HEADER", "format": "IMAGE", "example": { "header_handle": ["https://example.com/sample-image.jpg"] } } Use this when the template header should contain an image. The example should be a sample image handle or URL when available. 4. Video header { "type": "HEADER", "format": "VIDEO", "example": { "header_handle": ["https://example.com/sample-video.mp4"] } } Use this when the template header should contain a video. The example should be a sample video handle or URL when available. 5. Document header { "type": "HEADER", "format": "DOCUMENT", "example": { "header_handle": ["https://example.com/sample-document.pdf"] } } Use this when the template header should contain a document. The example should be a sample document handle or URL when available. 6. Location header { "type": "HEADER", "format": "LOCATION" } Use this when the template should display a location/map header. Important: - For template creation, LOCATION is only the header format. - Do not put latitude, longitude, address, or name in the template creation component. - The actual location values are supplied later when sending the approved template, not when creating the template. 7. Body without variables { "type": "BODY", "text": "Your order has shipped and is on the way." } Use this for the main message text. 8. Body with variables { "type": "BODY", "text": "Hi {{1}}, your order {{2}} has shipped.", "example": { "body_text": [ ["Alice", "ORD-12345"] ] } } Rules: - If body text contains variables, include example.body_text. - body_text is an array containing one array of sample values. - The inner array values must match the variables in order of appearance. - Use placeholders like {{1}}, {{2}}. 9. Footer { "type": "FOOTER", "text": "Reply STOP to unsubscribe." } Rules: - Footer is plain text only. - Do not use variables in footer text. 10. Buttons wrapper { "type": "BUTTONS", "buttons": [ Button ] } Rules: - Buttons must be inside a single component whose type is "BUTTONS". - Do not place button objects directly in components. - Button text should be short and action-oriented. Button variants: A. Quick reply button { "type": "QUICK_REPLY", "text": "Confirm" } Use when the user should tap a predefined reply. B. Phone number button { "type": "PHONE_NUMBER", "text": "Call us", "phone_number": "+15551234567" } Use when the user should call a business phone number. phone_number must include country code. C. Static URL button { "type": "URL", "text": "View order", "url": "https://example.com/orders" } Use when the button always opens the same URL. D. Dynamic URL button { "type": "URL", "text": "View order", "url": "https://example.com/orders/{{1}}", "example": ["ORD-12345"] } Rules: - Use this when the final URL path or query contains a variable. - The example array contains the sample value for the dynamic URL part. E. Copy code button { "type": "COPY_CODE", "example": "SAVE20" } Use for coupon or promo-code templates. The button copies the provided code when the template is sent. G. OTP button { "type": "OTP", "otp_type": "COPY_CODE", "text": "Copy code" } For one-tap OTP: { "type": "OTP", "otp_type": "ONE_TAP", "text": "Copy code", "autofill_text": "Autofill", "package_name": "com.example.app", "signature_hash": "abc123" } Rules: - Use OTP buttons only for authentication templates - category should be "AUTHENTICATION". Authentication templates can only be created for WABAs that have a 2,000 messaging limit or above. - Do not use marketing or utility wording in authentication templates. Examples: Utility order update with named parameters: { "name": "order_shipped_update", "language": "en_US", "category": "UTILITY", "components": [ { "type": "HEADER", "format": "TEXT", "text": "Order {{1}} update", "example": { "header_text": [["ORD-12345"]] } }, { "type": "BODY", "text": "Hi {{1}}, your order has shipped and should arrive by {{2}}.", "example": { "body_text": [ ["Alice", "Friday"] ] } }, { "type": "FOOTER", "text": "Thank you for shopping with us." }, { "type": "BUTTONS", "buttons": [ { "type": "URL", "text": "Track order", "url": "https://example.com/orders/{{1}}", "exam… [449 more characters not shown]
Annotations the server declares
- title: Create template
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
delete_templateDelete a WhatsApp message template by its internal template ID.No findings
Why it is in this group
- The name "delete_template" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Delete a WhatsApp message template by its internal template ID.
Annotations the server declares
- title: Delete template
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
enable_local_storageStore a channel's message data in a chosen region.Reads text others writeNo findings
Why it is in this group
- The name "enable_local_storage" says "enable": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Store a channel's message data in a chosen region. The channel is re-registered in Cloud API after calling this tool. Contact our support team if this tool fails.
Annotations the server declares
- title: Enable local storage
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
inbox_apply_saved_responseSend a saved (canned) response into a conversation as a text message.Reads text others writeNo findings
Why it is in this group
- The name "inbox_apply_saved_response" says "apply": a word for a change.
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Send a saved (canned) response into a conversation as a text message. Subject to the same 24-hour window rule as inbox_send_message.
Annotations the server declares
- title: Apply saved response
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
inbox_assign_conversationAssign or reassign one conversation to an agent and/or a group.No findings
Why it is in this group
- The name "inbox_assign_conversation" says "assign": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Assign or reassign one conversation to an agent and/or a group. Both fields are always set to exactly what you pass: calling with only `user_id` clears any group assignment and vice versa; calling with neither unassigns the conversation entirely.
Annotations the server declares
- title: Assign conversation
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
inbox_mark_conversation_as_readMark one conversation's messages as read by the calling user.Reads text others writeNo findings
Why it is in this group
- The name "inbox_mark_conversation_as_read" says "mark": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Mark one conversation's messages as read by the calling user. Pass `up_to_timestamp` after reviewing a conversation so that messages arriving in the meantime stay unread. The read mark only moves forward: a timestamp older than the caller's current mark changes nothing. Read state is per inbox user: this clears the unread count for the caller only, not for other agents. The inbox also marks the messages as read on WhatsApp, so the contact sees read receipts. Only conversations whose messages you can read can be marked.
Annotations the server declares
- title: Mark conversation as read
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
inbox_send_messageSend a message into an existing conversation, as the business.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "inbox_send_message" says "send": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "inbox_send_message" says "send": it sends or publishes something to other people.
Description, as the server wrote it Send a message into an existing conversation, as the business. This is inbox-scoped sending: it posts into an existing conversation with correct threading. Outside the 24-hour customer-care window, WhatsApp only permits template messages — other types are rejected with an explanation.
Annotations the server declares
- title: Send message
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
inbox_tag_conversationAdd or remove one tag on one conversation.No findings
Why it is in this group
- The description's first verb is "add": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Add or remove one tag on one conversation.
Annotations the server declares
- title: Tag conversation
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
invite_userInvite a new user to the account, with a role.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "invite_user" says "invite": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "invite_user" says "invite": it sends or publishes something to other people.
Description, as the server wrote it Invite a new user to the account, with a role. The invitee gets an email with a link to set their password. Client users invite to their own client account, partner users to the partner account. To create a new client together with its first user, use 'create_client_and_invite'. The user may be prompted by 360Dialog for an OTP code delivered to their email address.
Annotations the server declares
- title: Invite user
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
mba_delete_agentRemove the Meta Business Agent from this channel's WhatsApp number.Reads text others writeNo findings
Why it is in this group
- The name "mba_delete_agent" says "delete": a word for removing or ending something.
- The description says "irreversible".
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Remove the Meta Business Agent from this channel's WhatsApp number. Deletes the agent configuration and, when the last agent on the account is removed, disconnects the integration entirely. Returns {deleted_agent_id}. This is irreversible: knowledge, skills and connectors configured on the agent go with it, and restoring the setup means onboarding again from scratch.
Annotations the server declares
- title: Delete the agent
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_delete_agent_skillDelete one agent skill by its id, so the agent stops following it.Reads text others writeNo findings
Why it is in this group
- The name "mba_delete_agent_skill" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Delete one agent skill by its id, so the agent stops following it. Returns no content on success.
Annotations the server declares
- title: Delete an agent skill
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_delete_connectorDelete one connector by its id.Reads text others write1 finding
Why it is in this group
- The name "mba_delete_connector" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...nnector by its id. Its tools and stored credentials go with it. Returns no content on succe..."
Description, as the server wrote it Delete one connector by its id. Its tools and stored credentials go with it. Returns no content on success.
Annotations the server declares
- title: Delete a connector
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_delete_connector_toolDelete one connector tool definition by its id, so the agent can no longer perform that action.Reads text others writeNo findings
Why it is in this group
- The name "mba_delete_connector_tool" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Delete one connector tool definition by its id, so the agent can no longer perform that action. Returns no content on success.
Annotations the server declares
- title: Delete a connector tool
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_delete_faqDelete one FAQ entry by its id.Reads text others writeNo findings
Why it is in this group
- The name "mba_delete_faq" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Delete one FAQ entry by its id. Returns no content on success.
Annotations the server declares
- title: Delete an FAQ
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_delete_fileDelete one file from the agent's knowledge base by its id.Reads text others writeNo findings
Why it is in this group
- The name "mba_delete_file" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Delete one file from the agent's knowledge base by its id. Returns no content on success.
Annotations the server declares
- title: Delete a knowledge file
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_delete_ui_skillDelete one UI skill by its id, so the agent stops sending that component.Reads text others writeNo findings
Why it is in this group
- The name "mba_delete_ui_skill" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Delete one UI skill by its id, so the agent stops sending that component. Returns no content on success. To stop the component temporarily, set status to `disabled` with mba_update_ui_skill instead.
Annotations the server declares
- title: Delete a UI skill
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_delete_websiteRemove one website crawl entry by its id, dropping the knowledge crawled from it.Reads text others writeNo findings
Why it is in this group
- The name "mba_delete_website" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it Remove one website crawl entry by its id, dropping the knowledge crawled from it. Returns no content on success.
Annotations the server declares
- title: Remove a crawled website
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_remove_allowlist_entryRemove one entry from the allowlist by its entry id, which comes from mba_list_allowlist_entries (it is not the phone number).Reads text others writeNo findings
Why it is in this group
- The name "mba_remove_allowlist_entry" says "remove": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Remove one entry from the allowlist by its entry id, which comes from mba_list_allowlist_entries (it is not the phone number). Returns no content on success. While ai_audience is ALLOWLISTED_ONLY, removing the entry stops the agent answering that consumer.
Annotations the server declares
- title: Remove an allowlisted number
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_replace_agent_budgetsSet the usage caps for the agent.Reads text others writeNo findings
Why it is in this group
- The name "mba_replace_agent_budgets" says "replace": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Set the usage caps for the agent. Returns the caps in force after the write. This is a FULL REPLACEMENT of the set: send again every cap to keep, because any cap left out is removed, and an empty array clears all caps and returns the agent to unlimited. To edit an existing cap, pass back its budget_id from mba_get_agent_budgets; omit budget_id to add a new cap. Two caps with the same unit_type and time_window pair are rejected. Known limitations: budgets are ONLY SERVED for the business that owns this number's WABA; any other business_id is refused with an error that says so. For a number whose business is not known to 360dialog yet, budgets are not available and this tool returns an error that says so. When several caps are set, whichever is reached first stops the agent until its window resets, and the agent then hands conversations to the business. Token caps apply across the WHOLE BUSINESS MANAGER, so every agent in that portfolio shares them; AI-turn caps apply per conversation. These tools set and read caps and do not report usage against them: mba_get_agent_usage_insights reports billed usage, keyed on the billable account ID and not on business_id.
Annotations the server declares
- title: Replace the agent budgets
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_reset_business_infoReset the agent's business information to empty defaults and return the emptied object.Reads text others writeNo findings
Why it is in this group
- The name "mba_reset_business_info" says "reset": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Reset the agent's business information to empty defaults and return the emptied object. Unlike most deletes this does not 404 afterwards - mba_get_business_info keeps working and returns the defaults. Known limitation: business info is a CLOSED six-field schema - business_description, contact_info, delivery_and_shipping, payment_method, purchase_info, return_policy. Any other key is rejected. Knowledge that does not fit one of these six fields belongs in an FAQ (mba_create_faq), an agent skill (mba_create_agent_skill), a crawled website (mba_create_website) or an uploaded file (mba_upload_file) - not here.
Annotations the server declares
- title: Reset business info
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_run_connector_toolExecute one connector tool once, as the agent would, and return what the third-party system answered.Reads text others writeNo findings
Why it is in this group
- The name "mba_run_connector_tool" says "run": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Execute one connector tool once, as the agent would, and return what the third-party system answered. Use it to check a definition works before relying on it. `input` is a JSON-ENCODED STRING of the arguments, not an object. Known limitation: the result is DOUBLY STRINGIFIED - the response is {output, status} where `output` is a JSON string; parse `output`, then parse its `.body` to reach the third-party system's actual response. What this call does depends entirely on the tool being run: it can create, change or delete data in the connected system.
Annotations the server declares
- title: Run a connector tool
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_update_agent_settingsReplace the agent's settings and return the updated entry.Reads text others writeNo findings
Why it is in this group
- The name "mba_update_agent_settings" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Replace the agent's settings and return the updated entry. Known limitation: this is a FULL REPLACEMENT, not a patch - every field you omit is reset, so read the current settings with mba_get_agent_settings first and send them back with your change applied. Note also that setting rollout.enabled to false stops the AI responding on all threads; re-enabling it makes the AI respond to new threads only, not to threads that were already open.
Annotations the server declares
- title: Update agent settings
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_update_agent_skillReplace one agent skill by its id.Reads text others writeNo findings
Why it is in this group
- The name "mba_update_agent_skill" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Replace one agent skill by its id. This replaces the skill rather than patching it, so send the title, description and skill text you want it to end up with.
Annotations the server declares
- title: Update an agent skill
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_update_business_infoReplace the agent's business information and return the stored object.Reads text others writeNo findings
Why it is in this group
- The name "mba_update_business_info" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Replace the agent's business information and return the stored object. Known limitation: this is a FULL REPLACEMENT - fields you omit are cleared, so read mba_get_business_info first and send the existing values back with your change applied. Known limitation: business info is a CLOSED six-field schema - business_description, contact_info, delivery_and_shipping, payment_method, purchase_info, return_policy. Any other key is rejected. Knowledge that does not fit one of these six fields belongs in an FAQ (mba_create_faq), an agent skill (mba_create_agent_skill), a crawled website (mba_create_website) or an uploaded file (mba_upload_file) - not here.
Annotations the server declares
- title: Update business info
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_update_connectorReplace one connector by its id.Reads text others write5 findings
Why it is in this group
- The name "mba_update_connector" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.auth_config.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.auth_config.description: "Credentials matching auth_type: `api_key` when auth..."
- Info
The input schema at properties.auth_config.properties.api_key.properties.headers.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.headers.items.properties.value.description: "The credential value."
- Info
The input schema at properties.auth_config.properties.api_key.properties.query_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.query_params.items.properties.value.description: "The credential value."
- Info
The input schema at properties.auth_config.properties.api_key.properties.body_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.body_params.items.properties.value.description: "The credential value."
- Info
The input schema at properties.auth_config.properties.oauth2_client_credentials.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.oauth2_client_credentials.description: "OAuth 2.0 client credentials."
Description, as the server wrote it Replace one connector by its id. This replaces the connector rather than patching it, so send the full definition you want it to end up with - read mba_get_connector first.
Annotations the server declares
- title: Update a connector
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_update_connector_toolReplace one connector tool definition by its id.Reads text others write1 finding
Why it is in this group
- The name "mba_update_connector_tool" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.user_auth_required.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.user_auth_required.description: "...r token rather than the connector's own credentials."
Description, as the server wrote it Replace one connector tool definition by its id. This replaces the definition rather than patching it, so send the whole request_definition you want it to end up with - read mba_get_connector_tool first. Known limitation: path_parameters, query_parameters and headers are NAME-TO-SCHEMA OBJECTS, not arrays - write {"order_id": {"type": "string"}}, never [{"name": "order_id", ...}]. And every {brace} token in `path` must have a matching key in path_parameters, or the definition is rejected.
Annotations the server declares
- title: Update a connector tool
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_update_faqReplace one FAQ entry by its id.Reads text others writeNo findings
Why it is in this group
- The name "mba_update_faq" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Replace one FAQ entry by its id. Both question and answer are required: this replaces the entry rather than patching it, so send the fields you want the entry to end up with.
Annotations the server declares
- title: Update an FAQ
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_update_websiteReplace the URL of one website crawl entry.Reads text others writeNo findings
Why it is in this group
- The name "mba_update_website" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it Replace the URL of one website crawl entry. Changing the URL restarts crawling.
Annotations the server declares
- title: Update a crawled website
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_upsert_connector_api_keySet or rotate the API key credentials for a connector.Reads text others write4 findings
Why it is in this group
- The name "mba_upsert_connector_api_key" says "upsert": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "Set or rotate the API key credentials for a connector. This is an upsert: if..."
- Info
The input schema at properties.api_key_config.properties.headers.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.api_key_config.properties.headers.items.properties.value.description: "The credential value."
- Info
The input schema at properties.api_key_config.properties.query_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.api_key_config.properties.query_params.items.properties.value.description: "The credential value."
- Info
The input schema at properties.api_key_config.properties.body_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.api_key_config.properties.body_params.items.properties.value.description: "The credential value."
Description, as the server wrote it Set or rotate the API key credentials for a connector. This is an upsert: if credentials already exist they are REPLACED and the connection is re-established. It cannot be used to remove credentials - the payload is required.
Annotations the server declares
- title: Set connector API key
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_upsert_connector_certificateUpload or rotate the mTLS client certificate for a connector.Reads text others write1 finding
Why it is in this group
- The name "mba_upsert_connector_certificate" says "upsert": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...for a connector. This is an upsert: if credentials already exist they are REPLACED and the..."
Description, as the server wrote it Upload or rotate the mTLS client certificate for a connector. This is an upsert: if credentials already exist they are REPLACED and the connection is re-established. It cannot be used to remove credentials - the payload is required. Certificates and keys are PEM-encoded; the private key is never returned by any read tool.
Annotations the server declares
- title: Set connector mTLS certificate
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
mba_upsert_connector_oauthSet or rotate the OAuth 2.0 client credentials for a connector.Reads text others write4 findings
Why it is in this group
- The name "mba_upsert_connector_oauth" says "upsert": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The title mentions "credentials".
What this check looks forMatched text
title: "Set connector OAuth credentials"
- Info
The annotations title mentions "credentials".
What this check looks forMatched text
annotations.title: "Set connector OAuth credentials"
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "Set or rotate the OAuth 2.0 client credentials for a connector. This is an upsert: if..."
- Info
The input schema at properties.oauth_config.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.oauth_config.description: "OAuth 2.0 client credentials."
Description, as the server wrote it Set or rotate the OAuth 2.0 client credentials for a connector. This is an upsert: if credentials already exist they are REPLACED and the connection is re-established. It cannot be used to remove credentials - the payload is required.
Annotations the server declares
- title: Set connector OAuth credentials
- readOnlyHint: false
- destructiveHint: true
- openWorldHint: true
request_otpRequest an OTP code.No findings
Why it is in this group
- The name "request_otp" says "request": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Request an OTP code. Sometimes OTP is needed to complete invoking a tool. When tool invocation fails due to OTP reasons, you will be notified in the tool response, and be asked to rqeuest an OTP code. Only call after a tool call fails due to OTP. In clients that show apps, the user enters the code in a card shown with the result, and the result says so.
Annotations the server declares
- title: Request OTP
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
sandbox_configure_webhookSet webhook for the channel on 360Dialog sandbox.No findings
Why it is in this group
- The description's first verb is "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Set webhook for the channel on 360Dialog sandbox. Optional.
Annotations the server declares
- title: (Sandbox) Configure webhook
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
sandbox_register_numberRegister the user's phone number on the 360Dialog sandbox.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Register the user's phone number on the 360Dialog sandbox. Upon registration, the user can send messages to this phone number from the 360Dialog sandbox account on WhatsApp. The user will be given a link to complete registration. When this link is used, they will send a verification code to 360Dialog sandbox phone number on WhatsApp. They can click the link, or alternatively scan the QR code.
Annotations the server declares
- title: (Sandbox) Register number
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
sandbox_send_messageSend a message on the 360Dialog sandbox.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "sandbox_send_message" says "send": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "sandbox_send_message" says "send": it sends or publishes something to other people.
Description, as the server wrote it Send a message on the 360Dialog sandbox. Messages can only be sent to the user's phone number that was used during sandbox registration. The payload must be a JSON string matching the WhatsApp messages endpoint body. Interactive message example: use this only when there is an active conversation window, which lasts 24 hours since the customer's last message. { "messaging_product": "whatsapp", "to": "{{recipient_phone_number}}", "type": "text", "text": { "body": "{{message_body}}" } } Template message example: use this when there is no active conversation window, or when sending an approved template message. You can only send the 'marketing_message' template. { "messaging_product": "whatsapp", "to": "{{recipient_phone_number}}", "type": "template", "template": { "name": "marketing_message", "language": { "policy": "deterministic", "code": "en" }, "components": [ { "type": "header", "parameters": [ { "type": "image", "image": { "link": "https://placehold.co/600x315/34D399/FFFFFF/png?text=Summer+Sale!" } } ] } ] } }
Annotations the server declares
- title: (Sandbox) Send message
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
send_test_webhook_eventSend sample events to a channel's (a.k.a.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "send_test_webhook_event" says "send": a word for sending, and what is sent cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "send_test_webhook_event" says "send": it sends or publishes something to other people.
Description, as the server wrote it Send sample events to a channel's (a.k.a. phone number's) or a WABA's webhook, so the user can check that the webhook receives them and answers with a 2xx code. Pass exactly one of 'channel_id' or 'waba_account_id'. The user may see several sample requests arrive at their webhook server. Returns which sample events passed and which failed.
Annotations the server declares
- title: Send test webhook event
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
set_business_usernameClaim or change the WhatsApp business username of a channel.Reads text others writeNo findings
Why it is in this group
- The name "set_business_username" says "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Claim or change the WhatsApp business username of a channel. This changes what WhatsApp users see for the business, because the username can be shown instead of the phone number. Meta may reject the username, in which case an error is returned.
Annotations the server declares
- title: Set business username
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
set_display_nameSubmit a new display name for this channel (a.k.a.Reads text others writeNo findings
Why it is in this group
- The name "set_display_name" says "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Submit a new display name for this channel (a.k.a. phone number.) Calling this tool will submit a display name request to Meta. Meta takes up to 48 hours to review the submitted display name. The display name may be rejected if it does not comply with display name guidelines. The user will receive an email when their display name review is complete. When this tool is called, the user may be prompted by 360Dialog for an OTP code delivered to their email address.
Annotations the server declares
- title: Set display name
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
set_webhookSet a channel's (a.k.a.No findings
Why it is in this group
- The name "set_webhook" says "set": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Set a channel's (a.k.a. phone number's) webhook URL and optionally webhook headers.
Annotations the server declares
- title: Set webhook
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
subscribe_platform_status_updatesSubscribe the user to 360Dialog status update emails.Reads text others writeNo findings
Why it is in this group
- The name "subscribe_platform_status_updates" says "subscribe": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Subscribe the user to 360Dialog status update emails.
Annotations the server declares
- title: Subscribe to platform status updates
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
unblock_usersUnblock WhatsApp users so they can message a channel again.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Unblock WhatsApp users so they can message a channel again. Identify each user by phone number or by BSUID; pass at least one of 'phone_numbers' and 'user_ids'. For a user that 'list_blocked_users' shows without a phone number, pass the BSUID in 'user_ids'. The result lists which users were unblocked and which failed with the reason.
Annotations the server declares
- title: Unblock users
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
unsubscribe_platform_status_updatesStop 360Dialog status update emails for the user.Reads text others writeNo findings
Why it is in this group
- The name "unsubscribe_platform_status_updates" says "unsubscribe": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Stop 360Dialog status update emails for the user.
Annotations the server declares
- title: Unsubscribe from platform status updates
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
update_channel_profileUpdate the WhatsApp profile for this channel (a.k.a.Reads text others writeNo findings
Why it is in this group
- The name "update_channel_profile" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Update the WhatsApp profile for this channel (a.k.a. phone number.) The user may be prompted by 360Dialog for an OTP code delivered to their email address. Make them aware of the OTP requirement.
Annotations the server declares
- title: Update channel profile
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: true
update_commerce_settingsTurn the catalog visibility and the cart on or off for a channel.Reads text others writeNo findings
Why it is in this group
- The name "update_commerce_settings" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Turn the catalog visibility and the cart on or off for a channel. This changes what WhatsApp users see in the chat with the business. Pass at least one of 'catalog_visible' and 'cart_enabled'; a value that is left out keeps its current setting.
Annotations the server declares
- title: Update commerce settings
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
update_company_detailsSet the user's company's details on 360Dialog.No findings
Why it is in this group
- The name "update_company_details" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Set the user's company's details on 360Dialog. This change does not affect Meta; only records on 360Dialog are affected by the update. Before calling this tool, make sure to: 1. Check if the `get_company_details` tool returns the correct company information already. 2. Check with the user if they want to change their company details in 360Dialog. 3. Get the user's approval/confirmation.
Annotations the server declares
- title: Set company details
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
verify_otpVerify the 6-digit OTP code from the user.No findings
Why it is in this group
- The input takes a statement or command to run (input.code), which can change anything it can reach.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Verify the 6-digit OTP code from the user. Doing so will automatically replay the blocked tool call that required verification, except for tools whose result is shown to the user in an app: for those, the result says to call the tool again.
Annotations the server declares
- title: Verify OTP
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
Can't be undone 4Claude Code: ask
mba_release_thread_controlHand a consumer conversation back to the Meta Business Agent as the automatic responder, after a human agent has taken it over.Reads text others writeCan send data outNo findings
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Description, as the server wrote it Hand a consumer conversation back to the Meta Business Agent as the automatic responder, after a human agent has taken it over. Only releasing is supported here - taking control is restricted to configured escalation partners.
Annotations the server declares
- title: Release thread control
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_send_agent_eventTrigger the agent to act on a consumer conversation asynchronously - the event is queued and the call returns immediately with status "accepted" and an agent_event_id.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "mba_send_agent_event" says "send": a word for sending, and what is sent cannot be taken back.
- The input addresses people (input.to): what it sends cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "mba_send_agent_event" says "send": it sends or publishes something to other people.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Description, as the server wrote it Trigger the agent to act on a consumer conversation asynchronously - the event is queued and the call returns immediately with status "accepted" and an agent_event_id. Poll mba_get_agent_event with that id to find out what happened; a 202-style acknowledgement here does not mean the consumer was messaged. Known limitation: event.payload must be a JSON-ESCAPED STRING, not an object - pass "{\"order_id\":\"123\"}", not {"order_id": "123"}. Maximum 4096 characters.
Annotations the server declares
- title: Send an agent event
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_send_messageSend a WhatsApp message to a consumer and release thread control back to the agent.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "mba_send_message" says "send": a word for sending, and what is sent cannot be taken back.
- The input addresses people (input.to): what it sends cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "mba_send_message" says "send": it sends or publishes something to other people.
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Description, as the server wrote it Send a WhatsApp message to a consumer and release thread control back to the agent. The body is the WhatsApp Cloud API message object - set `type` and the matching payload key (text, template, interactive, image, ...). This messages a real person: it is subject to the platform's send eligibility rules, and outside a 24-hour customer service window only an approved template will be delivered.
Annotations the server declares
- title: Send a WhatsApp message
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_test_agentSend a test message through the full agent pipeline and read its reply, without needing a real consumer number.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe description's first verb is "send": it sends or publishes something to other people.
Description, as the server wrote it Send a test message through the full agent pipeline and read its reply, without needing a real consumer number. Pass conversation_id from a previous reply to continue the same test conversation. Known limitation: while ai_audience is ALLOWLISTED_ONLY this returns agent_response: "" with no_response_reason: "ELIGIBILITY_CHECK_FAILED", no matter which consumer number is involved - check mba_get_agent_settings before concluding the agent is broken.
Annotations the server declares
- title: Test the agent
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
Changes things 16Claude Code: ask
check_number_eligibilityCheck whether a phone number can be onboarded for this client before handing over the onboarding link.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- outboundThe input takes a destination (input.phone_number): what the tool writes goes there.
Description, as the server wrote it Check whether a phone number can be onboarded for this client before handing over the onboarding link. This tool only checks 360Dialog's own database and this client's channel quota. It does not ask WhatsApp/Meta anything, so a number already active on WhatsApp elsewhere (including the personal app) can still come back eligible here.
Annotations the server declares
- title: Check number eligibility
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
mba_add_allowlist_entryAdd one consumer phone number to the allowlist.Reads text others writeNo findings
Why it is in this group
- The name "mba_add_allowlist_entry" says "add": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Add one consumer phone number to the allowlist. Returns the created {id, consumer_phone_number}. The allowlist only takes effect while ai_audience is ALLOWLISTED_ONLY; under EVERYONE the agent answers all consumers regardless of this list.
Annotations the server declares
- title: Add an allowlisted number
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_check_agent_eligibilityCheck whether this channel's WhatsApp number is eligible for a Meta Business Agent.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Check whether this channel's WhatsApp number is eligible for a Meta Business Agent. Returns {is_eligible: boolean}. Known limitation: a 403 from this call can mean the number is simply not eligible, rather than that the business has not accepted Meta's terms - do not report an unaccepted-terms problem on a 403 alone.
Annotations the server declares
- title: Check agent eligibility
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_create_agent_skillAdd a skill to the agent - an instruction text that changes how it answers.Reads text others writeNo findings
Why it is in this group
- The name "mba_create_agent_skill" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Add a skill to the agent - an instruction text that changes how it answers. Returns the created skill with its id. Skills are the right home for behavioural instructions; facts the agent should know belong in FAQs, websites or files instead.
Annotations the server declares
- title: Create an agent skill
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_create_connectorCreate a connector so the agent can call a third-party system.Reads text others write5 findings
Why it is in this group
- The name "mba_create_connector" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.auth_config.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.auth_config.description: "Credentials matching auth_type: `api_key` when auth..."
- Info
The input schema at properties.auth_config.properties.api_key.properties.headers.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.headers.items.properties.value.description: "The credential value."
- Info
The input schema at properties.auth_config.properties.api_key.properties.query_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.query_params.items.properties.value.description: "The credential value."
- Info
The input schema at properties.auth_config.properties.api_key.properties.body_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.body_params.items.properties.value.description: "The credential value."
- Info
The input schema at properties.auth_config.properties.oauth2_client_credentials.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.oauth2_client_credentials.description: "OAuth 2.0 client credentials."
Description, as the server wrote it Create a connector so the agent can call a third-party system. Returns the connector with its id and connection_status. A connector on its own does nothing - add connector tools with mba_create_connector_tool to expose individual operations to the agent.
Annotations the server declares
- title: Create a connector
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_create_connector_toolDefine one action the agent can perform through a connector - an outbound HTTP request against the connector's base_url.Reads text others write1 finding
Why it is in this group
- The name "mba_create_connector_tool" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The input schema at properties.user_auth_required.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.user_auth_required.description: "...r token rather than the connector's own credentials."
Description, as the server wrote it Define one action the agent can perform through a connector - an outbound HTTP request against the connector's base_url. Returns the created tool with its id. Known limitation: path_parameters, query_parameters and headers are NAME-TO-SCHEMA OBJECTS, not arrays - write {"order_id": {"type": "string"}}, never [{"name": "order_id", ...}]. And every {brace} token in `path` must have a matching key in path_parameters, or the definition is rejected.
Annotations the server declares
- title: Create a connector tool
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_create_faqAdd one question-and-answer entry to the agent's knowledge.Reads text others writeNo findings
Why it is in this group
- The name "mba_create_faq" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Add one question-and-answer entry to the agent's knowledge. Returns the created entry with its id. FAQs are the right home for knowledge that does not fit business info's six fields.
Annotations the server declares
- title: Create an FAQ
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_create_ui_skillGive the agent one more rich WhatsApp component to send, and the instruction that says when to send it.Reads text others writeNo findings
Why it is in this group
- The name "mba_create_ui_skill" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Give the agent one more rich WhatsApp component to send, and the instruction that says when to send it. Returns the created UI skill with its id. A UI skill is NOT an agent skill (mba_list_agent_skills): an agent skill is instruction text that shapes what the agent says, a UI skill lets the agent send one kind of rich WhatsApp component and tells it when to send that component. Known limitation: component_type is FIXED AT CREATION and cannot be changed afterwards. flow_id is required when component_type is `flow`, and is refused for every other type; a flow UI skill also cannot be enabled until the flow itself is published.
Annotations the server declares
- title: Create a UI skill
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_create_websiteAdd a website URL for the agent to crawl into its knowledge base.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "mba_create_website" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Add a website URL for the agent to crawl into its knowledge base. Returns the entry with its id and crawl status. Crawling is asynchronous - the knowledge is not available immediately; poll mba_get_website for crawl_status.
Annotations the server declares
- title: Add a website to crawl
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_onboard_agentCreate the Meta Business Agent for this channel on the given messaging channel.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a destination (input.channel): what the tool writes goes there.
Description, as the server wrote it Create the Meta Business Agent for this channel on the given messaging channel. Creates the underlying entities and schedules asynchronous data-preparation jobs, so the agent is not immediately ready to answer. Returns {agent_id}. Onboarding does not switch the agent on: rollout stays disabled until mba_update_agent_settings enables it.
Annotations the server declares
- title: Onboard the agent
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_start_eval_runSubmit an evaluation job that simulates the listed cases against the agent, evaluates the conversations and optionally produces insights.Reads text others writeNo findings
Why it is in this group
- The name "mba_start_eval_run" says "start": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Submit an evaluation job that simulates the listed cases against the agent, evaluates the conversations and optionally produces insights. Returns {job_id, status: QUEUED} - the work is asynchronous, so poll mba_get_eval_results with the job_id. Known limitation: eval_case_ids is read from the QUERY STRING, not the request body - pass it as the comma-separated argument here and this service puts it in the right place; the body is a separate object that accepts nothing else.
Annotations the server declares
- title: Start an evaluation run
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_update_ui_skillChange the title, the status or the instruction of one UI skill by its id.Reads text others writeNo findings
Why it is in this group
- The name "mba_update_ui_skill" says "update": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Change the title, the status or the instruction of one UI skill by its id. This is a partial update: a field you omit keeps its stored value. Use it to enable or disable a component without deleting it. A UI skill is NOT an agent skill (mba_list_agent_skills): an agent skill is instruction text that shapes what the agent says, a UI skill lets the agent send one kind of rich WhatsApp component and tells it when to send that component. Known limitation: component_type and flow_id cannot be changed - delete the UI skill and create a new one instead. A flow UI skill cannot be enabled until its flow is published.
Annotations the server declares
- title: Update a UI skill
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
mba_upload_fileUpload a file into the agent's knowledge base.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "mba_upload_file" says "upload": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Upload a file into the agent's knowledge base. Multipart uploads cannot travel over MCP, so pass the file EITHER as `url` (a publicly reachable https URL this service downloads) OR as `content_base64` (the file's bytes, base64-encoded) - exactly one of the two, always with `file_name`. This service performs the multipart upload to Meta for you and returns the created {id, file_name}. Known limitations: Meta caps a file at 100 MB and accepts PDF, DOC, DOCX, PNG, JPG and JPEG (CSV and XLSX where enabled). Base64 content is additionally capped by this endpoint's request size limit, so prefer `url` for anything larger than a few megabytes. A `url` must be https and must resolve to a public address - private, loopback and link-local addresses are refused.
Annotations the server declares
- title: Upload a knowledge file
- readOnlyHint: false
- destructiveHint: false
- openWorldHint: true
sandbox_complete_registrationComplete a phone number's registration.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Complete a phone number's registration. This will get you the API key to use when sending messages from the 360Dialog sandbox phone number to the user's registered phone number.
Annotations the server declares
- title: (Sandbox) Complete registration
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
start_number_onboardingGet the link that lets the user connect a WhatsApp phone number in 360Dialog, plus what to tell them beforehand.1 finding
Why it is in this group
- The name "start_number_onboarding" says "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "start_number_onboarding" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "start_number_onboarding" says "start": a word for a change.
Description, as the server wrote it Get the link that lets the user connect a WhatsApp phone number in 360Dialog, plus what to tell them beforehand. This hands over 360Dialog's own onboarding page. The user clicks through Embedded Signup themselves; this tool cannot do it for them. The user must be signed in to 360Dialog Hub already, or the link sends them to login first and loses the destination. Tell them to make sure they're signed in first. The link given by this tool may not work if the user's 360Dialog client account is under a partner-paid channel. Make them aware of this. Returns the client's current channel IDs for future reference on recognizing which phone number was newly added.
Annotations the server declares
- title: Start number onboarding
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
start_signupReturns the URL where a user can create a 360Dialog account.1 finding
Why it is in this group
- The name "start_signup" says "start": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "start_signup" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "start_signup" says "start": a word for a change.
Description, as the server wrote it Returns the URL where a user can create a 360Dialog account. Only relevant if the user has not created a 360Dialog account yet.
Annotations the server declares
- title: Get 360Dialog signup link
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 69Show 69 read-only tools
get_business_username_suggestionsSuggest available WhatsApp business usernames for a channel.No findings
Why it is in this group
- The name "get_business_username_suggestions" says "get": a word for reading.
Description, as the server wrote it Suggest available WhatsApp business usernames for a channel. Meta reserves these usernames for the number's business. Use this before 'set_business_username'.
Annotations the server declares
- title: Get business username suggestions
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_channel_detailsShow the full details of one channel: status, availability, quality rating, messaging limit, registration code status, and its WABA, project, client and app IDs.No findings
Why it is in this group
- The name "get_channel_details" says "get": a word for reading.
Description, as the server wrote it Show the full details of one channel: status, availability, quality rating, messaging limit, registration code status, and its WABA, project, client and app IDs. Also shows the channel's WhatsApp Business Account (WABA): its status, Meta business verification status, message-on-behalf status, phone number and conversation limits, Meta ban state, and any policy violations affecting this number. Use it to troubleshoot restricted or unverified accounts. Useful for when the user asks more details for a specific number. Use 'list_channels' to find channels first.
Annotations the server declares
- title: Get channel details
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_channel_profileGet a channel's (a.k.a.No findings
Why it is in this group
- The name "get_channel_profile" says "get": a word for reading.
Description, as the server wrote it Get a channel's (a.k.a. phone number) WhatsApp profile, and the profile's 360Dialog Hub page.
Annotations the server declares
- title: Get channel profile
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_client_detailsShow one client's account details and status: name, status, number limit, contact information and Meta business ID.Reads private dataNo findings
Why it is in this group
- The name "get_client_details" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "show" and "contact": it reads contacts.
Description, as the server wrote it Show one client's account details and status: name, status, number limit, contact information and Meta business ID. Client users see their own account. Partner users pass the ID of one of their clients.
Annotations the server declares
- title: Get client details
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_client_documentation_pageGet a documentation page from the 360Dialog client documentation at https://docs.360dialog.com/docs.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "get_client_documentation_page" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "doc": it reads documents.
- untrusted-inputThe description's first sentence says "get" and "http": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Get a documentation page from the 360Dialog client documentation at https://docs.360dialog.com/docs. Fetch the full markdown content of a specific documentation page from Client Documentation. Use this when you have a page URL and want to read its content. Accepts full URLs (e.g. https://docs.360dialog.com/docs/getting-started). Since `searchDocumentation` returns partial content, use `getPage` to retrieve the complete page when you need more details. The content includes links you can follow to navigate to related pages.
Annotations the server declares
- title: Get client documentation page
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_commerce_settingsShow whether the WhatsApp Business catalog is visible and the cart is enabled on a channel.No findings
Why it is in this group
- The name "get_commerce_settings" says "get": a word for reading.
Description, as the server wrote it Show whether the WhatsApp Business catalog is visible and the cart is enabled on a channel.
Annotations the server declares
- title: Get commerce settings
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_company_detailsGet the user's company's details from 360Dialog.No findings
Why it is in this group
- The name "get_company_details" says "get": a word for reading.
Description, as the server wrote it Get the user's company's details from 360Dialog.
Annotations the server declares
- title: Get company details
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_currency_migration_statusShow the progress of a WABA's billing currency change.No findings
Why it is in this group
- The name "get_currency_migration_status" says "get": a word for reading.
Description, as the server wrote it Show the progress of a WABA's billing currency change. Returns the most recent migration, or says there is none.
Annotations the server declares
- title: Get currency migration status
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_messaging_analyticsShow messages sent, delivered and billed for a phone number (channel) over a date range, and their cost.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_messaging_analytics" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "show" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "show" and "message": it reads messages, which other people can write.
Description, as the server wrote it Show messages sent, delivered and billed for a phone number (channel) over a date range, and their cost. Without dates it covers the last 7 days; ranges over 90 days are summarised by month. Days follow the WhatsApp Business Account's timezone, and today (or this month) appears only once it's over. Rate limited, so prefer one call covering the whole range.
Annotations the server declares
- title: Get messaging analytics
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_onboarding_statusGet a phone number's status on whether a number is live, what type of messages it can send today, and suggestions for what's next.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_onboarding_status" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "message": it reads messages.
- untrusted-inputThe description's first sentence says "get" and "message": it reads messages, which other people can write.
Description, as the server wrote it Get a phone number's status on whether a number is live, what type of messages it can send today, and suggestions for what's next. A live number can send free-form replies inside the 24-hour customer service window immediately (meaning if someone messages the number, the user can respond to the message using the API). Template messages are separately blocked until Meta reviews a submitted template (template reviews take up to 24 hours.) Lack of business verification is not a blocker. Unverified businesses can only send 250 templates to unique users per 24 hours.
Annotations the server declares
- title: Get onboarding status
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_platform_statusCheck whether 360Dialog or WhatsApp currently has an outage or degraded service.Reads text others writeNo findings
Why it is in this group
- The name "get_platform_status" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Check whether 360Dialog or WhatsApp currently has an outage or degraded service. Use this first when messages fail, webhooks stop, or the user asks whether the platform is down.
Annotations the server declares
- title: Get platform status
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
get_selfGet currently logged in user's information in 360Dialog.No findings
Why it is in this group
- The name "get_self" says "get": a word for reading.
Description, as the server wrote it Get currently logged in user's information in 360Dialog. You will get: - user's name, - user's email address, - partner name, - user's permissions in 360Dialog Hub, - user's roles
Annotations the server declares
- title: Get current user
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_skillGet the full guide for one skill returned by 'list_skills', as markdown.No findings
Why it is in this group
- The name "get_skill" says "get": a word for reading.
Description, as the server wrote it Get the full guide for one skill returned by 'list_skills', as markdown.
Annotations the server declares
- title: Get skill
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_template_json_exampleSending messaging templates in WhatsApp API / 360Dialog API requires a JSON body in the API request.No findings
Why it is in this group
- The name "get_template_json_example" says "get": a word for reading.
Description, as the server wrote it Sending messaging templates in WhatsApp API / 360Dialog API requires a JSON body in the API request. The API request can be hard to form, as the body must declare in JSON what each parameter in the JSON should be filled as. This tool creates a valid example JSON body that the user can later modify before sending the template to WhatsApp users. It is recommended that you use this tool after creating a template, or after the user asks how to send a template. Display the JSON result of this tool.
Annotations the server declares
- title: Get template JSON example
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_voice_analyticsShow the number, duration and cost of calls for a phone number (channel) over a date range.No findings
Why it is in this group
- The name "get_voice_analytics" says "get": a word for reading.
Description, as the server wrote it Show the number, duration and cost of calls for a phone number (channel) over a date range. Without dates it covers the last 7 days; ranges over 90 days are summarised by month. Days follow the WhatsApp Business Account's timezone, and today (or this month) appears only once it's over. Rate limited, so prefer one call covering the whole range.
Annotations the server declares
- title: Get voice analytics
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_webhookGet a channel's (a.k.a.No findings
Why it is in this group
- The name "get_webhook" says "get": a word for reading.
Description, as the server wrote it Get a channel's (a.k.a. phone number's) webhook URL, and check if the optional webhook headers are set. Webhook headers are optional. They can be set using the 'set_webhook' tool, which also sets the webhook URL. When webhook headers are set, 360Dialog will send webhooks to the channel's webhook URL and add the specified headers. This helps only authenticated requests pass through app firewalls, if the user has any. Example: If webhook URL is `https://foo.com/webhook`, and webhook headers are set to {"x-360dialog-webhook-security": "RANDOM-STRING"}, the webhook URL will receive POST requests like this: POST https://foo.com/webhook HEADERS x-360dialog-webhook-security: RANDOM-STRING
Annotations the server declares
- title: Get webhook
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
inbox_get_conversationRead one conversation: contact/assignment/tag details plus its message history.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "inbox_get_conversation" says "get": a word for reading.
What it can reach
- private-dataThe name "inbox_get_conversation" says "get" and "inbox": it reads mail.
- private-dataThe description's first sentence says "read" and "conversation": it reads messages.
- untrusted-inputThe name "inbox_get_conversation" says "get" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "read" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it Read one conversation: contact/assignment/tag details plus its message history. Messages are returned newest first. To page further back, call again with `before_time` set to the oldest returned message's timestamp.
Annotations the server declares
- title: Get conversation
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
inbox_list_agentsList the inbox's agents (users) — for assignment via inbox_assign_conversation.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "inbox_list_agents" says "list": a word for reading.
What it can reach
- private-dataThe name "inbox_list_agents" says "list" and "inbox": it reads mail.
- private-dataThe description's first sentence says "list" and "inbox": it reads mail.
- untrusted-inputThe name "inbox_list_agents" says "list" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "inbox": it reads inbound email, which other people can write.
Description, as the server wrote it List the inbox's agents (users) — for assignment via inbox_assign_conversation.
Annotations the server declares
- title: List agents
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
inbox_list_conversationsList conversations of the inbox, newest activity first.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "inbox_list_conversations" says "list": a word for reading.
What it can reach
- private-dataThe name "inbox_list_conversations" says "list" and "inbox": it reads mail.
- private-dataThe description's first sentence says "list" and "conversation": it reads messages.
- untrusted-inputThe name "inbox_list_conversations" says "list" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it List conversations of the inbox, newest activity first. Returns one entry per conversation with contact info, unread count, last message, current assignee (user and/or group), and tags.
Annotations the server declares
- title: List conversations
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
inbox_list_groupsList the inbox's agent groups — for group assignment via inbox_assign_conversation.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "inbox_list_groups" says "list": a word for reading.
What it can reach
- private-dataThe name "inbox_list_groups" says "list" and "inbox": it reads mail.
- private-dataThe description's first sentence says "list" and "inbox": it reads mail.
- untrusted-inputThe name "inbox_list_groups" says "list" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "inbox": it reads inbound email, which other people can write.
Description, as the server wrote it List the inbox's agent groups — for group assignment via inbox_assign_conversation.
Annotations the server declares
- title: List groups
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
inbox_list_inboxesList the WhatsApp inboxes the calling 360dialog user can access.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "inbox_list_inboxes" says "list": a word for reading.
What it can reach
- private-dataThe name "inbox_list_inboxes" says "list" and "inbox": it reads mail.
- private-dataThe description's first sentence says "list" and "inbox": it reads mail.
- untrusted-inputThe name "inbox_list_inboxes" says "list" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "inbox": it reads inbound email, which other people can write.
Description, as the server wrote it List the WhatsApp inboxes the calling 360dialog user can access. Call this first when you don't know which `channel_id` to pass to the other tools: each entry pairs a `channel_id` with its inbox URL and WhatsApp number (`wa_id`). Entries without a `channel_id` cannot be driven through these tools. The listing covers the caller's own client accounts, plus every inbox under a partner the caller administers. It never reaches another tenant: a client user is not shown other clients' inboxes, including ones managed by the same partner. An empty list does not mean no inbox exists; pass a known `channel_id` to the other tools directly.
Annotations the server declares
- title: List inboxes
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
inbox_list_saved_responsesList the inbox's saved (canned) responses — for use with inbox_apply_saved_response.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "inbox_list_saved_responses" says "list": a word for reading.
What it can reach
- private-dataThe name "inbox_list_saved_responses" says "list" and "inbox": it reads mail.
- private-dataThe description's first sentence says "list" and "inbox": it reads mail.
- untrusted-inputThe name "inbox_list_saved_responses" says "list" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "inbox": it reads inbound email, which other people can write.
Description, as the server wrote it List the inbox's saved (canned) responses — for use with inbox_apply_saved_response.
Annotations the server declares
- title: List saved responses
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
inbox_list_tagsList the inbox's tags — for tagging via inbox_tag_conversation and filtering via inbox_list_conversations.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "inbox_list_tags" says "list": a word for reading.
What it can reach
- private-dataThe name "inbox_list_tags" says "list" and "inbox": it reads mail.
- private-dataThe description's first sentence says "list" and "inbox": it reads mail.
- untrusted-inputThe name "inbox_list_tags" says "list" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "inbox": it reads inbound email, which other people can write.
Description, as the server wrote it List the inbox's tags — for tagging via inbox_tag_conversation and filtering via inbox_list_conversations.
Annotations the server declares
- title: List tags
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
inbox_search_conversationsFind conversations by contact name, phone number, tag name, or message content.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "inbox_search_conversations" says "search": a word for reading.
What it can reach
- private-dataThe name "inbox_search_conversations" says "search" and "inbox": it reads mail.
- private-dataThe description's first sentence says "find" and "conversation": it reads messages.
- untrusted-inputThe name "inbox_search_conversations" says "search" and "inbox": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "find" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it Find conversations by contact name, phone number, tag name, or message content. Searches contact profiles and tags first, then message text and media captions; results from both are merged and deduplicated by conversation. Each match notes why it matched (`contact` or `message_content`).
Annotations the server declares
- title: Search conversations
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_blocked_usersShow which WhatsApp users are blocked from messaging a channel.No findings
Why it is in this group
- The name "list_blocked_users" says "list": a word for reading.
Description, as the server wrote it Show which WhatsApp users are blocked from messaging a channel. Meta always returns the BSUID; phone number is only returned when it has been shared with the business. To unblock a user without a phone number, pass their BSUID to 'unblock_users' in 'user_ids'.
Annotations the server declares
- title: List blocked users
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_channelsFind a channel by passing in an identifier.No findings
Why it is in this group
- The name "list_channels" says "list": a word for reading.
Description, as the server wrote it Find a channel by passing in an identifier. A channel is a phone number. By calling this tool you retrieve information about the phone number/channel in 360Dialog. Results are paginated; use the 'page' and 'size' arguments to page through results if there are more than fit in a single page. Returns: If no channel matches, returns "No channels found." If found, returns information of channels, like WABA ID, client ID, channel ID, app ID and the number's 360Dialog Hub page, along with the current page, total pages, and total count.
Annotations the server declares
- title: List channels
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_partner_change_requestsList requests to move numbers between partners, with their status.No findings
Why it is in this group
- The name "list_partner_change_requests" says "list": a word for reading.
Description, as the server wrote it List requests to move numbers between partners, with their status. Client users see the requests their client made. Partner users see the requests addressed to their partner, which they can approve or reject; a partner can pass 'client_id' to only see the requests of one client. Pass 'request_id' to follow the status of one request.
Annotations the server declares
- title: List partner change requests
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_platform_status_subscriptionsList the user's 360Dialog status update subscriptions (delivered via email).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_platform_status_subscriptions" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "email": it reads mail.
- untrusted-inputThe description's first sentence says "list" and "email": it reads inbound email, which other people can write.
Description, as the server wrote it List the user's 360Dialog status update subscriptions (delivered via email).
Annotations the server declares
- title: List platform status subscriptions
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_skillsList the 360Dialog skills available to you.No findings
Why it is in this group
- The name "list_skills" says "list": a word for reading.
Description, as the server wrote it List the 360Dialog skills available to you. A skill is a curated, up-to-date how-to guide for a 360Dialog process (e.g. drafting a compliant WhatsApp template, diagnosing a channel that stopped sending). Call this tool BEFORE answering any "how do I..." question about 360Dialog products or processes - it tells you which skills exist and when to use them. Once you find a match, call 'get_skill' with its 'name' to read the full guide.
Annotations the server declares
- title: List skills
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_templatesList templates for a WABA (WhatsApp Business Account).No findings
Why it is in this group
- The name "list_templates" says "list": a word for reading.
Description, as the server wrote it List templates for a WABA (WhatsApp Business Account). If you do not have a waba_account_id ending in 'WA' (case-insensitive), run the 'list_channels' tool first.
Annotations the server declares
- title: List templates
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_usersList users of the selected account, including their roles and creation timestamps.No findings
Why it is in this group
- The name "list_users" says "list": a word for reading.
Description, as the server wrote it List users of the selected account, including their roles and creation timestamps. Client users get the users of their own client account, partner users the users of the partner account.
Annotations the server declares
- title: List users
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
mba_get_agent_budgetsRead the usage caps in force for the agent, each with its budget_id.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_agent_budgets" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read the usage caps in force for the agent, each with its budget_id. Returns {budgets}; an empty array means no cap is set and usage is unlimited. Known limitations: budgets are ONLY SERVED for the business that owns this number's WABA; any other business_id is refused with an error that says so. For a number whose business is not known to 360dialog yet, budgets are not available and this tool returns an error that says so. When several caps are set, whichever is reached first stops the agent until its window resets, and the agent then hands conversations to the business. Token caps apply across the WHOLE BUSINESS MANAGER, so every agent in that portfolio shares them; AI-turn caps apply per conversation. These tools set and read caps and do not report usage against them: mba_get_agent_usage_insights reports billed usage, keyed on the billable account ID and not on business_id.
Annotations the server declares
- title: Read the agent budgets
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_agent_eventRead the processing status of an event submitted with mba_send_agent_event.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_agent_event" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read the processing status of an event submitted with mba_send_agent_event. Status is one of request_received, processing, sent, failed, skipped or success; failed and skipped carry error_message and skipped_reason. This is the only way to find out whether an accepted event actually reached the consumer.
Annotations the server declares
- title: Read agent event status
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_agent_event_insightsRead what happened to the events sent to the agent (mba_send_agent_event) over a date range, one row per event type, busiest first: how many were received, how many the agent succe…Reads text others writeNo findings
Why it is in this group
- The name "mba_get_agent_event_insights" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read what happened to the events sent to the agent (mba_send_agent_event) over a date range, one row per event type, busiest first: how many were received, how many the agent successfully processed, and the mean end-to-end latency. Successfully processed means the agent sent its message, not that the message was delivered. Figures are rolled up once a day, so the most recent day may still be incomplete. Known limitation: the dates are in PACIFIC TIME, not the business time zone, and the range may span at most 30 days, counting both ends.
Annotations the server declares
- title: Read agent event insights
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_agent_settingsRead the agent's current settings: rollout, handoff, followup and ai_audience.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_agent_settings" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read the agent's current settings: rollout, handoff, followup and ai_audience. Known limitation: this returns an ARRAY with one entry per channel, not a single object. Read the entry whose `channel` you care about (usually "whatsapp") rather than treating the response as an object.
Annotations the server declares
- title: Read agent settings
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_agent_skillRead one agent skill by its id, as returned by mba_list_agent_skills or mba_create_agent_skill.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_agent_skill" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read one agent skill by its id, as returned by mba_list_agent_skills or mba_create_agent_skill.
Annotations the server declares
- title: Read an agent skill
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_agent_stateRead whether this channel has ever been onboarded and whether its agent has ever been activated, as {onboarded, activated_once}.No findings
Why it is in this group
- The name "mba_get_agent_state" says "get": a word for reading.
Description, as the server wrote it Read whether this channel has ever been onboarded and whether its agent has ever been activated, as {onboarded, activated_once}. Known limitation: this is NOT a Meta call - it reads this service's own tracking record, written when onboarding or a settings read/write goes through here. It answers 'did onboarding ever succeed' and 'was rollout ever enabled', and nothing about the agent's current configuration. For live state call mba_get_agent_settings.
Annotations the server declares
- title: Read agent state
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
mba_get_agent_usage_insightsRead the billed usage of a Meta Business Agent account over a billing date range, one entry per HOUR, DAY or MONTH bucket: billable messages, billable tokens, and cost in the accou…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "mba_get_agent_usage_insights" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "message": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "read" and "message": it reads messages, which other people can write.
Description, as the server wrote it Read the billed usage of a Meta Business Agent account over a billing date range, one entry per HOUR, DAY or MONTH bucket: billable messages, billable tokens, and cost in the account's currency. Returns {usage}; an empty array means no usage in the range. Each entry carries its bucket start and end (Unix seconds, end exclusive), plus channel and sender_id when they are in dimensions. Metrics left out of metric_types are omitted from every entry, not returned as null. Tokens are BILLED tokens, the figure on the invoice, which can be fewer than the tokens the agent consumed. Known limitations: usage insights are ONLY AVAILABLE for numbers whose stack uses its own WABA access token; for any other number this tool returns an error that says so. The range is start INCLUSIVE, end EXCLUSIVE, and dates are evaluated in the billable account's timezone, so a day bucket can be 23 or 25 hours long. MONTH needs a range of whole months: start on the 1st, end on the last day of a month.
Annotations the server declares
- title: Read agent usage insights
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_business_infoRead the business information the agent uses to answer customers.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_business_info" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read the business information the agent uses to answer customers. Returns empty or default values when none has been configured. Known limitation: business info is a CLOSED six-field schema - business_description, contact_info, delivery_and_shipping, payment_method, purchase_info, return_policy. Any other key is rejected. Knowledge that does not fit one of these six fields belongs in an FAQ (mba_create_faq), an agent skill (mba_create_agent_skill), a crawled website (mba_create_website) or an uploaded file (mba_upload_file) - not here.
Annotations the server declares
- title: Read business info
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_commerce_settingsRead this channel's WhatsApp commerce settings: whether the cart is enabled and whether the catalog is visible in the chat and on the business profile.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "mba_get_commerce_settings" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "chat": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "read" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Read this channel's WhatsApp commerce settings: whether the cart is enabled and whether the catalog is visible in the chat and on the business profile. Returns {data: [one entry]} with is_cart_enabled and is_catalog_visible.
Annotations the server declares
- title: Read commerce settings
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_connectorRead one connector by its id, including its connection_status and mTLS metadata.Reads text others write1 finding
Why it is in this group
- The name "mba_get_connector" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Info
The description mentions "Credentials".
What this check looks forMatched text
description: "...ts connection_status and mTLS metadata. Credentials are never returned - the private key an..."
Description, as the server wrote it Read one connector by its id, including its connection_status and mTLS metadata. Credentials are never returned - the private key and secrets stay at Meta.
Annotations the server declares
- title: Read a connector
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_connector_logsRead the connector's third-party error logs, or aggregated failure patterns when summary_only is true.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_connector_logs" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read the connector's third-party error logs, or aggregated failure patterns when summary_only is true. Only errors from the third-party system are included, so an empty result means no failures, not no traffic. Known limitation: the time range must not exceed 7 DAYS, and only the last 7 days are retained - start_time defaults to 24 hours ago and end_time to now. Unlike the other list tools this one does return an object: {data: [...], stats: {...}}, with stats present only when include_stats is true.
Annotations the server declares
- title: Read connector logs
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_connector_toolRead one connector tool definition by its id.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_connector_tool" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read one connector tool definition by its id.
Annotations the server declares
- title: Read a connector tool
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_conversation_insightsRead how many conversations the agent replied in over a date range (ai_threads), and how many are currently handed from the agent to the business and still awaiting a business repl…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "mba_get_conversation_insights" says "get": a word for reading.
What it can reach
- private-dataThe name "mba_get_conversation_insights" says "get" and "conversation": it reads messages.
- private-dataThe description's first sentence says "read" and "conversation": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "mba_get_conversation_insights" says "get" and "conversation": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "read" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it Read how many conversations the agent replied in over a date range (ai_threads), and how many are currently handed from the agent to the business and still awaiting a business reply (ai_handoffs). Counts are per conversation, not per message, and match the business's own agent summaries. Returns {data: [one row]}, each metric as {count}, present only when requested. Known limitation: ai_handoffs is a SNAPSHOT of the present moment - it ignores start_date and end_date. The range may span at most 90 days, counting both ends, and each requested metric costs a separate scan, so ask only for what you need.
Annotations the server declares
- title: Read conversation insights
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_conversation_turnsRead the ordered turns of the most recent conversation between the agent and one customer.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "mba_get_conversation_turns" says "get": a word for reading.
What it can reach
- private-dataThe name "mba_get_conversation_turns" says "get" and "conversation": it reads messages.
- private-dataThe description's first sentence says "read" and "conversation": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "mba_get_conversation_turns" says "get" and "conversation": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "read" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it Read the ordered turns of the most recent conversation between the agent and one customer. Each turn carries its turn_id, conversation_id and the observed steps - LLM calls with a preview of the model output, and tool calls with the tool name, input and output - plus latency and status where available. Use it to see why the agent answered the way it did. Malformed records, and tool responses that cannot be matched to a tool call, may be missing. This list is CURSOR-PAGINATED: it returns {data, paging} - page with the `after` cursor from paging.cursors, and stop when paging carries no `next` link, because a page can be empty and still have more after it.
Annotations the server declares
- title: Read conversation turns
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_eval_detailsRead per-conversation evaluation results - scores, per-turn labels, reasons and the transcript.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "mba_get_eval_details" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "conversation": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "read" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it Read per-conversation evaluation results - scores, per-turn labels, reasons and the transcript. Takes eval_ids, which is a different kind of id from the job_id that mba_get_eval_results takes. Read them from the eval_ids_by_score field of a completed job. mba_get_eval_results already adds these details when it can read that field, so call this tool when it could not.
Annotations the server declares
- title: Read evaluation details
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_eval_resultsRead an evaluation job by its job_id.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_eval_results" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read an evaluation job by its job_id. While the job runs this gives the status (QUEUED or RUNNING) and the progress. When the job fails it gives the error. When the job completes it gives the aggregated report: the summary text, the average conversation and turn scores, the highlights and the top failure categories. There is no separate summary call: a completed job already carries that report. For the per-conversation transcripts and per-turn labels, take the ids from `eval_ids_by_score` and call mba_get_eval_details. This tool adds a `details` key when it can read those ids for you.
Annotations the server declares
- title: Read evaluation results
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_faqRead one FAQ entry by its id, as returned by mba_list_faqs or mba_create_faq.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_faq" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read one FAQ entry by its id, as returned by mba_list_faqs or mba_create_faq.
Annotations the server declares
- title: Read an FAQ
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_fileRead one knowledge file's metadata by its id.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "mba_get_file" says "get": a word for reading.
What it can reach
- private-dataThe name "mba_get_file" says "get" and "file": it reads files.
- private-dataThe description's first sentence says "read" and "file": it reads files.
- private-dataThe input names a file (input.file_id), and the tool reads: it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read one knowledge file's metadata by its id. Returns {id, file_name} - this returns metadata only, not the file's contents.
Annotations the server declares
- title: Read knowledge file metadata
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_tool_call_insightsRead how each of the business's own tools performed over a date range, one row per tool, busiest first: how many conversations called it, its mean latency, and its success, error a…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "mba_get_tool_call_insights" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "conversation": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "read" and "conversation": it reads messages, which other people can write.
Description, as the server wrote it Read how each of the business's own tools performed over a date range, one row per tool, busiest first: how many conversations called it, its mean latency, and its success, error and timeout rates (0 to 1; timeouts count as errors too). Only tools the business supplied are reported. thread_count counts a conversation once per day, so one that called the tool on three days counts three times. Figures are rolled up once a day, so the most recent day may still be incomplete. Known limitation: the range may span at most 30 days, counting both ends.
Annotations the server declares
- title: Read tool call insights
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_ui_skillRead one UI skill by its id, as returned by mba_list_ui_skills or mba_create_ui_skill.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_ui_skill" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Read one UI skill by its id, as returned by mba_list_ui_skills or mba_create_ui_skill. A UI skill is NOT an agent skill (mba_list_agent_skills): an agent skill is instruction text that shapes what the agent says, a UI skill lets the agent send one kind of rich WhatsApp component and tells it when to send that component.
Annotations the server declares
- title: Read a UI skill
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_get_websiteRead one website crawl entry by its id, including crawl_status, pages_crawled and last_crawled_at.Reads text others writeNo findings
Why it is in this group
- The name "mba_get_website" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "mba_get_website" says "get" and "website": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it Read one website crawl entry by its id, including crawl_status, pages_crawled and last_crawled_at. This is how you check whether a site added with mba_create_website has been ingested yet.
Annotations the server declares
- title: Read a crawled website
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_agent_skillsList the agent's skills - the instruction texts that shape how it behaves.Reads text others writeNo findings
Why it is in this group
- The name "mba_list_agent_skills" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the agent's skills - the instruction texts that shape how it behaves. Known limitation: this returns a BARE ARRAY, not an object with a `data` key.
Annotations the server declares
- title: List agent skills
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_allowlist_entriesList the consumer phone numbers allowed to reach the agent while ai_audience is ALLOWLISTED_ONLY.Reads text others writeNo findings
Why it is in this group
- The name "mba_list_allowlist_entries" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the consumer phone numbers allowed to reach the agent while ai_audience is ALLOWLISTED_ONLY. Known limitation: this returns a BARE ARRAY of {id, consumer_phone_number}, not an object with a `data` key.
Annotations the server declares
- title: List allowlisted numbers
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_catalog_productsList the products of one catalog connected to this channel's WhatsApp Business Account.Reads text others writeNo findings
Why it is in this group
- The name "mba_list_catalog_products" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the products of one catalog connected to this channel's WhatsApp Business Account. A product's retailer_id is the product_retailer_id that product messages take. Known limitation: a catalog that is NOT CONNECTED to this WABA, or that does not exist, returns 403 Catalog not accessible - get valid ids from mba_list_product_catalogs. This list is CURSOR-PAGINATED: it returns {data, paging} - page with the `after` cursor from paging.cursors, and stop when paging carries no `next` link, because a page can be empty and still have more after it.
Annotations the server declares
- title: List catalog products
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_connector_toolsList the actions defined on one connector.Reads text others writeNo findings
Why it is in this group
- The name "mba_list_connector_tools" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the actions defined on one connector. Known limitation: this returns a BARE ARRAY, not an object with a `data` key.
Annotations the server declares
- title: List connector tools
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_connectorsList the agent's connectors - the third-party systems it can call.Reads text others writeNo findings
Why it is in this group
- The name "mba_list_connectors" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the agent's connectors - the third-party systems it can call. Each carries a connection_status (PENDING_OAUTH, ACTIVE, EXPIRED or ERROR) worth checking before relying on its tools. Known limitation: this returns a BARE ARRAY, not an object with a `data` key.
Annotations the server declares
- title: List connectors
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_eval_casesList the evaluation scenarios configured for this agent, each with its scenario text, categories, max_turns and success criteria.Reads text others writeNo findings
Why it is in this group
- The name "mba_list_eval_cases" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the evaluation scenarios configured for this agent, each with its scenario text, categories, max_turns and success criteria. Their ids are what mba_start_eval_run takes.
Annotations the server declares
- title: List evaluation cases
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_faqsList the agent's FAQ entries.Reads text others writeNo findings
Why it is in this group
- The name "mba_list_faqs" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the agent's FAQ entries. Known limitation: this returns a BARE ARRAY, not an object with a `data` key.
Annotations the server declares
- title: List FAQs
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_filesList the files in the agent's knowledge base, as {id, file_name}.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "mba_list_files" says "list": a word for reading.
What it can reach
- private-dataThe name "mba_list_files" says "list" and "file": it reads files.
- private-dataThe description's first sentence says "list" and "file": it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the files in the agent's knowledge base, as {id, file_name}. Known limitation: this returns a BARE ARRAY, not an object with a `data` key.
Annotations the server declares
- title: List knowledge files
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_product_catalogsList the Meta product catalogs connected to this channel's WhatsApp Business Account.Reads text others writeNo findings
Why it is in this group
- The name "mba_list_product_catalogs" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the Meta product catalogs connected to this channel's WhatsApp Business Account. Only id and name are returned unless `fields` asks for more. Use the catalog id with mba_list_catalog_products. This list is CURSOR-PAGINATED: it returns {data, paging} - page with the `after` cursor from paging.cursors, and stop when paging carries no `next` link, because a page can be empty and still have more after it.
Annotations the server declares
- title: List product catalogs
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_ui_skillsList the agent's UI skills - the rich WhatsApp components (carousels, CTA URLs, flows, images, interactive lists and buttons, location) the agent may send, each with the instructio…Reads text others writeNo findings
Why it is in this group
- The name "mba_list_ui_skills" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List the agent's UI skills - the rich WhatsApp components (carousels, CTA URLs, flows, images, interactive lists and buttons, location) the agent may send, each with the instruction that says when to send it. A UI skill is NOT an agent skill (mba_list_agent_skills): an agent skill is instruction text that shapes what the agent says, a UI skill lets the agent send one kind of rich WhatsApp component and tells it when to send that component. This list is CURSOR-PAGINATED: it returns {data, paging} - page with the `after` cursor from paging.cursors, and stop when paging carries no `next` link, because a page can be empty and still have more after it.
Annotations the server declares
- title: List UI skills
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
mba_list_websitesList the websites the agent crawls for knowledge, with their crawl status.Reads text others writeNo findings
Why it is in this group
- The name "mba_list_websites" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "mba_list_websites" says "list" and "website": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it List the websites the agent crawls for knowledge, with their crawl status. Known limitation: this returns a BARE ARRAY, not an object with a `data` key.
Annotations the server declares
- title: List crawled websites
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
preview_partner_change_requestCheck whether numbers can move to a new partner, without creating a request.No findings
Why it is in this group
- The name "preview_partner_change_request" says "preview": a word for reading.
Description, as the server wrote it Check whether numbers can move to a new partner, without creating a request. Runs the same pre-flight checks as 'create_partner_change_request' and reports every issue that would block the move (for example a number that cannot move, a missing company detail, or a request that is already in progress). Nothing is created or changed. Show the result to the user, then, if it is clear, call 'create_partner_change_request' with the same arguments.
Annotations the server declares
- title: Preview partner change request
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
sandbox_get_webhook_configurationGet configured webhook for the channel on 360Dialog sandbox.No findings
Why it is in this group
- The name "sandbox_get_webhook_configuration" says "get": a word for reading.
Description, as the server wrote it Get configured webhook for the channel on 360Dialog sandbox.
Annotations the server declares
- title: (Sandbox) Get webhook configuration
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
sandbox_list_eventsList webhook events received.No findings
Why it is in this group
- The name "sandbox_list_events" says "list": a word for reading.
Description, as the server wrote it List webhook events received. This will show received messages from the user, and status of messages sent from the sandbox account.
Annotations the server declares
- title: (Sandbox) List events
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
search_client_documentationSearch the 360Dialog client documentation at https://docs.360dialog.com/docs.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "search_client_documentation" says "search": a word for reading.
What it can reach
- private-dataThe description's first sentence says "search" and "doc": it reads documents.
- untrusted-inputThe description's first sentence says "search" and "http": it reads web pages, which anyone can write.
Description, as the server wrote it Search the 360Dialog client documentation at https://docs.360dialog.com/docs. Search across the documentation to find relevant information, code examples, API references, and guides. Use this tool when you need to answer questions about Client Documentation, find specific documentation, understand how features work, or locate implementation details. The search returns contextual content with titles and direct links to the documentation pages.
Annotations the server declares
- title: Search client documentation
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
show_template_previewShow a preview of a given template to the user.No findings
Why it is in this group
- The name "show_template_preview" says "show": a word for reading.
Description, as the server wrote it Show a preview of a given template to the user.
Annotations the server declares
- title: Show template preview
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
wait_for_onboarding_stepWait for a server-side onboarding step to finish, then report back.No findings
Why it is in this group
- The name "wait_for_onboarding_step" says "wait": a word for reading.
Description, as the server wrote it Wait for a server-side onboarding step to finish, then report back. Embedded Signup and payment setup finish in the person's browser. This tool polls the hub every 5 seconds for up to 45 seconds and returns one of: - "done": The step finished. - "pending": Still not finished. Call this tool again to keep waiting. - "failed": There was an error. 'channel_id' and 'phone_number' are returned back once a channel is found so you can pass 'phone_number' into the next call once you have it. When 'phone_number' is omitted, 'candidates' lists the client's most recently created channels - check it if you're unsure the right number was picked (e.g. two users connecting numbers on the same 360Dialog client account). Only use this for the short waits during onboarding. This tool is NOT suitable for display name approval, WABA approval, or business verification scenarios, as they take days, not seconds.
Annotations the server declares
- title: Wait for onboarding step
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
28314 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 13 outbound tools breaks every one.
- Reads private data22
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write99
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out13
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__360dialog__check_number_eligibility",
"mcp__360dialog__get_client_documentation_page",
"mcp__360dialog__inbox_send_message",
"mcp__360dialog__invite_user",
"mcp__360dialog__mba_create_website",
"mcp__360dialog__mba_onboard_agent",
"mcp__360dialog__mba_release_thread_control",
"mcp__360dialog__mba_send_agent_event",
"mcp__360dialog__mba_send_message",
"mcp__360dialog__mba_test_agent",
"mcp__360dialog__mba_upload_file",
"mcp__360dialog__sandbox_send_message",
"mcp__360dialog__send_test_webhook_event"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 16, 2026, 14:20 UTC, unchanged since Nov 16, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 69
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.360dialog.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://mcp.360dialog.com/
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 69 tools that change things (49 destructive, 4 irreversible, 16 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.360dialog.com/mcp: tools/list returned 135 tools to an anonymous client, including set_display_name (destructive), update_channel_profile (destructive), set_business_username (destructive), update_commerce_settings (destructive), enable_local_storage (destructive) and 64 more
Posture changes
- Nov 16, 2026
- Tools that change things, listed without credentials: 60 to 69
Findings
Matches of fixed checks, with the text they matched.
- Warnstart_signup
The server marks "start_signup" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "start_signup" says "start": a word for a change.
The server marks "start_number_onboarding" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "start_number_onboarding" says "start": a word for a change.
- Infocreate_template
The description is 6,449 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "..."body_text": [ ["Alice", "Downtown"] ] } } ] }"
The input schema at properties.auth_config.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.auth_config.description: "Credentials matching auth_type: `api_key` when auth..."
The input schema at properties.auth_config.properties.api_key.properties.headers.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.headers.items.properties.value.description: "The credential value."
The input schema at properties.auth_config.properties.api_key.properties.query_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.query_params.items.properties.value.description: "The credential value."
Show 20 more findingsShow fewer
The input schema at properties.auth_config.properties.api_key.properties.body_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.body_params.items.properties.value.description: "The credential value."
The input schema at properties.auth_config.properties.oauth2_client_credentials.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.oauth2_client_credentials.description: "OAuth 2.0 client credentials."
The description mentions "Credentials".
What this check looks forMatched text
description: "...ts connection_status and mTLS metadata. Credentials are never returned - the private key an..."
The input schema at properties.auth_config.description mentions "Credentials".
What this check looks forMatched text
inputSchema.properties.auth_config.description: "Credentials matching auth_type: `api_key` when auth..."
The input schema at properties.auth_config.properties.api_key.properties.headers.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.headers.items.properties.value.description: "The credential value."
The input schema at properties.auth_config.properties.api_key.properties.query_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.query_params.items.properties.value.description: "The credential value."
The input schema at properties.auth_config.properties.api_key.properties.body_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.api_key.properties.body_params.items.properties.value.description: "The credential value."
The input schema at properties.auth_config.properties.oauth2_client_credentials.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.auth_config.properties.oauth2_client_credentials.description: "OAuth 2.0 client credentials."
The description mentions "credentials".
What this check looks forMatched text
description: "...nnector by its id. Its tools and stored credentials go with it. Returns no content on succe..."
The description mentions "credentials".
What this check looks forMatched text
description: "Set or rotate the API key credentials for a connector. This is an upsert: if..."
The input schema at properties.api_key_config.properties.headers.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.api_key_config.properties.headers.items.properties.value.description: "The credential value."
The input schema at properties.api_key_config.properties.query_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.api_key_config.properties.query_params.items.properties.value.description: "The credential value."
The input schema at properties.api_key_config.properties.body_params.items.properties.value.description mentions "credential".
What this check looks forMatched text
inputSchema.properties.api_key_config.properties.body_params.items.properties.value.description: "The credential value."
The title mentions "credentials".
What this check looks forMatched text
title: "Set connector OAuth credentials"
The annotations title mentions "credentials".
What this check looks forMatched text
annotations.title: "Set connector OAuth credentials"
The description mentions "credentials".
What this check looks forMatched text
description: "Set or rotate the OAuth 2.0 client credentials for a connector. This is an upsert: if..."
The input schema at properties.oauth_config.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.oauth_config.description: "OAuth 2.0 client credentials."
The description mentions "credentials".
What this check looks forMatched text
description: "...for a connector. This is an upsert: if credentials already exist they are REPLACED and the..."
The input schema at properties.user_auth_required.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.user_auth_required.description: "...r token rather than the connector's own credentials."
The input schema at properties.user_auth_required.description mentions "credentials".
What this check looks forMatched text
inputSchema.properties.user_auth_required.description: "...r token rather than the connector's own credentials."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 added.+3 addedView diff
- Added:mba_get_commerce_settingsOnly reads
- Added:mba_list_catalog_productsOnly reads
- Added:mba_list_product_catalogsOnly reads
PostureRemote posture changed. Tools that change things, listed without credentials: 60 -> 69.View diff
- Tools that change things, listed without credentials: 60 to 69
Tools36 added, 17 removed, 15 changed.+36 added−17 removed~15 changedView diff
- Added:block_usersDeletes or cancels
- Added:change_user_roleDeletes or cancels
- Added:create_partner_change_requestDeletes or cancels
- Added:enable_local_storageDeletes or cancels
- Added:get_business_username_suggestionsOnly reads
- Added:get_channel_detailsOnly reads
- Added:get_client_detailsOnly reads
- Added:get_commerce_settingsOnly reads
- Added:get_currency_migration_statusOnly reads
- Added:get_messaging_analyticsOnly reads
- Added:get_platform_statusOnly reads
- Added:get_voice_analyticsOnly reads
- Added:inbox_apply_saved_responseDeletes or cancels
- Added:inbox_assign_conversationDeletes or cancels
- Added:inbox_get_conversationOnly reads
- Added:inbox_list_agentsOnly reads
- Added:inbox_list_conversationsOnly reads
- Added:inbox_list_groupsOnly reads
- Added:inbox_list_inboxesOnly reads
- Added:inbox_list_saved_responsesOnly reads
- Added:inbox_list_tagsOnly reads
- Added:inbox_mark_conversation_as_readDeletes or cancels
- Added:inbox_search_conversationsOnly reads
- Added:inbox_send_messageDeletes or cancels
- Added:inbox_tag_conversationDeletes or cancels
- Added:invite_userDeletes or cancels
- Added:list_blocked_usersOnly reads
- Added:list_partner_change_requestsOnly reads
- Added:list_platform_status_subscriptionsOnly reads
- Added:preview_partner_change_requestOnly reads
- Added:send_test_webhook_eventDeletes or cancels
- Added:set_business_usernameDeletes or cancels
- Added:subscribe_platform_status_updatesDeletes or cancels
- Added:unblock_usersDeletes or cancels
- Added:unsubscribe_platform_status_updatesDeletes or cancels
- Added:update_commerce_settingsDeletes or cancels
- Removed:get_balance
- Removed:get_invoices
- Removed:getchat_apply_saved_response
- Removed:getchat_assign_conversation
- Removed:getchat_get_conversation
- Removed:getchat_list_agents
- Removed:getchat_list_conversations
- Removed:getchat_list_groups
- Removed:getchat_list_inboxes
- Removed:getchat_list_saved_responses
- Removed:getchat_list_tags
- Removed:getchat_mark_conversation_as_read
- Removed:getchat_search_conversations
- Removed:getchat_send_message
- Removed:getchat_tag_conversation
- Removed:start_payment_setup
- Removed:test_webhook
- Changed:create_templateDeletes or cancelsinputSchema
- Changed:delete_templateDeletes or cancelsinputSchema
- Changed:get_channel_profileOnly readsdescriptioninputSchema
- Changed:get_onboarding_statusOnly readsdescriptioninputSchema
- Changed:get_template_json_exampleOnly readsinputSchema
- Changed:get_webhookOnly readsinputSchema
- Changed:list_channelsOnly readsdescriptioninputSchema
- Changed:list_templatesOnly readsinputSchema
- Changed:list_usersOnly readsdescription
- Changed:request_otpDeletes or cancelsdescription
- Changed:set_display_nameDeletes or cancelsinputSchema
- Changed:set_webhookDeletes or cancelsinputSchema
- Changed:show_template_previewOnly readsinputSchema
- Changed:update_channel_profileDeletes or cancelsinputSchema
- Changed:verify_otpDeletes or cancelsdescriptioninputSchema
Install
Pinned to version 2.2.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http 360dialog https://mcp.360dialog.com/mcpclaude mcp add --transport http 360dialog https://mcp.360dialog.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__360dialog__list_skills",
"mcp__360dialog__get_skill",
"mcp__360dialog__search_client_documentation",
"mcp__360dialog__get_messaging_analytics",
"mcp__360dialog__get_voice_analytics",
"mcp__360dialog__list_channels",
"mcp__360dialog__get_channel_profile",
"mcp__360dialog__get_channel_details",
"mcp__360dialog__get_business_username_suggestions",
"mcp__360dialog__get_commerce_settings",
"mcp__360dialog__list_blocked_users",
"mcp__360dialog__get_currency_migration_status",
"mcp__360dialog__wait_for_onboarding_step",
"mcp__360dialog__get_company_details",
"mcp__360dialog__get_onboarding_status",
"mcp__360dialog__get_platform_status",
"mcp__360dialog__list_platform_status_subscriptions",
"mcp__360dialog__list_templates",
"mcp__360dialog__show_template_preview",
"mcp__360dialog__get_template_json_example",
"mcp__360dialog__get_webhook",
"mcp__360dialog__get_self",
"mcp__360dialog__list_users",
"mcp__360dialog__sandbox_get_webhook_configuration",
"mcp__360dialog__sandbox_list_events",
"mcp__360dialog__get_client_details",
"mcp__360dialog__list_partner_change_requests",
"mcp__360dialog__preview_partner_change_request",
"mcp__360dialog__inbox_list_conversations",
"mcp__360dialog__inbox_search_conversations",
"mcp__360dialog__inbox_get_conversation",
"mcp__360dialog__inbox_list_inboxes",
"mcp__360dialog__inbox_list_agents",
"mcp__360dialog__inbox_list_groups",
"mcp__360dialog__inbox_list_tags",
"mcp__360dialog__inbox_list_saved_responses",
"mcp__360dialog__mba_get_agent_settings",
"mcp__360dialog__mba_list_allowlist_entries",
"mcp__360dialog__mba_get_business_info",
"mcp__360dialog__mba_list_faqs",
"mcp__360dialog__mba_get_faq",
"mcp__360dialog__mba_list_websites",
"mcp__360dialog__mba_get_website",
"mcp__360dialog__mba_list_files",
"mcp__360dialog__mba_get_file",
"mcp__360dialog__mba_list_agent_skills",
"mcp__360dialog__mba_get_agent_skill",
"mcp__360dialog__mba_list_ui_skills",
"mcp__360dialog__mba_get_ui_skill",
"mcp__360dialog__mba_list_product_catalogs",
"mcp__360dialog__mba_list_catalog_products",
"mcp__360dialog__mba_get_commerce_settings",
"mcp__360dialog__mba_get_agent_budgets",
"mcp__360dialog__mba_list_connectors",
"mcp__360dialog__mba_get_connector",
"mcp__360dialog__mba_get_connector_logs",
"mcp__360dialog__mba_list_connector_tools",
"mcp__360dialog__mba_get_connector_tool",
"mcp__360dialog__mba_get_agent_event",
"mcp__360dialog__mba_list_eval_cases",
"mcp__360dialog__mba_get_eval_results",
"mcp__360dialog__mba_get_eval_details",
"mcp__360dialog__mba_get_agent_event_insights",
"mcp__360dialog__mba_get_conversation_turns",
"mcp__360dialog__mba_get_conversation_insights",
"mcp__360dialog__mba_get_tool_call_insights",
"mcp__360dialog__mba_get_agent_usage_insights",
"mcp__360dialog__mba_get_agent_state"
],
"ask": [
"mcp__360dialog__start_signup",
"mcp__360dialog__get_client_documentation_page",
"mcp__360dialog__check_number_eligibility",
"mcp__360dialog__start_number_onboarding",
"mcp__360dialog__sandbox_complete_registration",
"mcp__360dialog__mba_check_agent_eligibility",
"mcp__360dialog__mba_onboard_agent",
"mcp__360dialog__mba_add_allowlist_entry",
"mcp__360dialog__mba_create_faq",
"mcp__360dialog__mba_create_website",
"mcp__360dialog__mba_upload_file",
"mcp__360dialog__mba_create_agent_skill",
"mcp__360dialog__mba_create_ui_skill",
"mcp__360dialog__mba_update_ui_skill",
"mcp__360dialog__mba_create_connector",
"mcp__360dialog__mba_create_connector_tool",
"mcp__360dialog__mba_send_agent_event",
"mcp__360dialog__mba_test_agent",
"mcp__360dialog__mba_release_thread_control",
"mcp__360dialog__mba_send_message",
"mcp__360dialog__mba_start_eval_run"
],
"deny": [
"mcp__360dialog__set_display_name",
"mcp__360dialog__update_channel_profile",
"mcp__360dialog__set_business_username",
"mcp__360dialog__update_commerce_settings",
"mcp__360dialog__enable_local_storage",
"mcp__360dialog__block_users",
"mcp__360dialog__unblock_users",
"mcp__360dialog__update_company_details",
"mcp__360dialog__request_otp",
"mcp__360dialog__verify_otp",
"mcp__360dialog__subscribe_platform_status_updates",
"mcp__360dialog__unsubscribe_platform_status_updates",
"mcp__360dialog__create_template",
"mcp__360dialog__delete_template",
"mcp__360dialog__set_webhook",
"mcp__360dialog__send_test_webhook_event",
"mcp__360dialog__invite_user",
"mcp__360dialog__change_user_role",
"mcp__360dialog__sandbox_register_number",
"mcp__360dialog__sandbox_send_message",
"mcp__360dialog__sandbox_configure_webhook",
"mcp__360dialog__create_partner_change_request",
"mcp__360dialog__inbox_send_message",
"mcp__360dialog__inbox_assign_conversation",
"mcp__360dialog__inbox_tag_conversation",
"mcp__360dialog__inbox_mark_conversation_as_read",
"mcp__360dialog__inbox_apply_saved_response",
"mcp__360dialog__mba_delete_agent",
"mcp__360dialog__mba_update_agent_settings",
"mcp__360dialog__mba_remove_allowlist_entry",
"mcp__360dialog__mba_update_business_info",
"mcp__360dialog__mba_reset_business_info",
"mcp__360dialog__mba_update_faq",
"mcp__360dialog__mba_delete_faq",
"mcp__360dialog__mba_update_website",
"mcp__360dialog__mba_delete_website",
"mcp__360dialog__mba_delete_file",
"mcp__360dialog__mba_update_agent_skill",
"mcp__360dialog__mba_delete_agent_skill",
"mcp__360dialog__mba_delete_ui_skill",
"mcp__360dialog__mba_replace_agent_budgets",
"mcp__360dialog__mba_update_connector",
"mcp__360dialog__mba_delete_connector",
"mcp__360dialog__mba_upsert_connector_api_key",
"mcp__360dialog__mba_upsert_connector_oauth",
"mcp__360dialog__mba_upsert_connector_certificate",
"mcp__360dialog__mba_update_connector_tool",
"mcp__360dialog__mba_delete_connector_tool",
"mcp__360dialog__mba_run_connector_tool"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as 360dialog. Review it before you use it.
Capability tags behind 101 rules
- mcp__360dialog__search_client_documentation private-data, untrusted-input
- mcp__360dialog__get_client_documentation_page private-data, untrusted-input, outbound
- mcp__360dialog__get_messaging_analytics private-data, untrusted-input
- mcp__360dialog__set_display_name untrusted-input
- mcp__360dialog__update_channel_profile untrusted-input
- mcp__360dialog__set_business_username untrusted-input
- mcp__360dialog__update_commerce_settings untrusted-input
- mcp__360dialog__enable_local_storage untrusted-input
- mcp__360dialog__block_users untrusted-input
- mcp__360dialog__unblock_users untrusted-input
- mcp__360dialog__check_number_eligibility outbound
- mcp__360dialog__get_onboarding_status private-data, untrusted-input
- mcp__360dialog__get_platform_status untrusted-input
- mcp__360dialog__list_platform_status_subscriptions private-data, untrusted-input
- mcp__360dialog__subscribe_platform_status_updates untrusted-input
- mcp__360dialog__unsubscribe_platform_status_updates untrusted-input
- mcp__360dialog__send_test_webhook_event untrusted-input, outbound
- mcp__360dialog__invite_user untrusted-input, outbound
- mcp__360dialog__sandbox_send_message untrusted-input, outbound
- mcp__360dialog__get_client_details private-data
- mcp__360dialog__create_partner_change_request untrusted-input
- mcp__360dialog__inbox_send_message untrusted-input, outbound
- mcp__360dialog__inbox_mark_conversation_as_read untrusted-input
- mcp__360dialog__inbox_apply_saved_response untrusted-input
- mcp__360dialog__inbox_list_conversations private-data, untrusted-input
- mcp__360dialog__inbox_search_conversations private-data, untrusted-input
- mcp__360dialog__inbox_get_conversation private-data, untrusted-input
- mcp__360dialog__inbox_list_inboxes private-data, untrusted-input
- mcp__360dialog__inbox_list_agents private-data, untrusted-input
- mcp__360dialog__inbox_list_groups private-data, untrusted-input
- mcp__360dialog__inbox_list_tags private-data, untrusted-input
- mcp__360dialog__inbox_list_saved_responses private-data, untrusted-input
- mcp__360dialog__mba_check_agent_eligibility untrusted-input
- mcp__360dialog__mba_onboard_agent untrusted-input, outbound
- mcp__360dialog__mba_delete_agent untrusted-input
- mcp__360dialog__mba_get_agent_settings untrusted-input
- mcp__360dialog__mba_update_agent_settings untrusted-input
- mcp__360dialog__mba_list_allowlist_entries untrusted-input
- mcp__360dialog__mba_add_allowlist_entry untrusted-input
- mcp__360dialog__mba_remove_allowlist_entry untrusted-input
- mcp__360dialog__mba_get_business_info untrusted-input
- mcp__360dialog__mba_update_business_info untrusted-input
- mcp__360dialog__mba_reset_business_info untrusted-input
- mcp__360dialog__mba_list_faqs untrusted-input
- mcp__360dialog__mba_create_faq untrusted-input
- mcp__360dialog__mba_get_faq untrusted-input
- mcp__360dialog__mba_update_faq untrusted-input
- mcp__360dialog__mba_delete_faq untrusted-input
- mcp__360dialog__mba_list_websites untrusted-input
- mcp__360dialog__mba_create_website untrusted-input, outbound
- mcp__360dialog__mba_get_website untrusted-input
- mcp__360dialog__mba_update_website untrusted-input
- mcp__360dialog__mba_delete_website untrusted-input
- mcp__360dialog__mba_list_files private-data, untrusted-input
- mcp__360dialog__mba_upload_file untrusted-input, outbound
- mcp__360dialog__mba_get_file private-data, untrusted-input
- mcp__360dialog__mba_delete_file untrusted-input
- mcp__360dialog__mba_list_agent_skills untrusted-input
- mcp__360dialog__mba_create_agent_skill untrusted-input
- mcp__360dialog__mba_get_agent_skill untrusted-input
- mcp__360dialog__mba_update_agent_skill untrusted-input
- mcp__360dialog__mba_delete_agent_skill untrusted-input
- mcp__360dialog__mba_list_ui_skills untrusted-input
- mcp__360dialog__mba_create_ui_skill untrusted-input
- mcp__360dialog__mba_get_ui_skill untrusted-input
- mcp__360dialog__mba_update_ui_skill untrusted-input
- mcp__360dialog__mba_delete_ui_skill untrusted-input
- mcp__360dialog__mba_list_product_catalogs untrusted-input
- mcp__360dialog__mba_list_catalog_products untrusted-input
- mcp__360dialog__mba_get_commerce_settings private-data, untrusted-input
- mcp__360dialog__mba_get_agent_budgets untrusted-input
- mcp__360dialog__mba_replace_agent_budgets untrusted-input
- mcp__360dialog__mba_list_connectors untrusted-input
- mcp__360dialog__mba_create_connector untrusted-input
- mcp__360dialog__mba_get_connector untrusted-input
- mcp__360dialog__mba_update_connector untrusted-input
- mcp__360dialog__mba_delete_connector untrusted-input
- mcp__360dialog__mba_upsert_connector_api_key untrusted-input
- mcp__360dialog__mba_upsert_connector_oauth untrusted-input
- mcp__360dialog__mba_upsert_connector_certificate untrusted-input
- mcp__360dialog__mba_get_connector_logs untrusted-input
- mcp__360dialog__mba_list_connector_tools untrusted-input
- mcp__360dialog__mba_create_connector_tool untrusted-input
- mcp__360dialog__mba_get_connector_tool untrusted-input
- mcp__360dialog__mba_update_connector_tool untrusted-input
- mcp__360dialog__mba_delete_connector_tool untrusted-input
- mcp__360dialog__mba_run_connector_tool untrusted-input
- mcp__360dialog__mba_send_agent_event untrusted-input, outbound
- mcp__360dialog__mba_get_agent_event untrusted-input
- mcp__360dialog__mba_test_agent untrusted-input, outbound
- mcp__360dialog__mba_release_thread_control untrusted-input, outbound
- mcp__360dialog__mba_send_message untrusted-input, outbound
- mcp__360dialog__mba_list_eval_cases untrusted-input
- mcp__360dialog__mba_start_eval_run untrusted-input
- mcp__360dialog__mba_get_eval_results untrusted-input
- mcp__360dialog__mba_get_eval_details private-data, untrusted-input
- mcp__360dialog__mba_get_agent_event_insights untrusted-input
- mcp__360dialog__mba_get_conversation_turns private-data, untrusted-input
- mcp__360dialog__mba_get_conversation_insights private-data, untrusted-input
- mcp__360dialog__mba_get_tool_call_insights private-data, untrusted-input
- mcp__360dialog__mba_get_agent_usage_insights private-data, untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.360dialog/mcp/verify?hash=80ade08ccfe03f0c1e8f5eceddf52bbe0df2a6a0ade9f1a282ac7d2711c6cfa9" | jq -e '.changed == false'Pinned hash 80ade08ccfe0, from Nov 19, 2026, 03:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.360dialog/mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.360dialog/mcp)Source: MCP Registry. Synced Nov 19, 2026, 03:17 UTC.
360dialog MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the 360dialog MCP server safe?
- No scan can promise that. What its definitions show: 138 tools, 69 of which can change, send or delete something, and 26 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the 360dialog MCP server delete data?
- Yes. 49 tools can delete, cancel or revoke something: set_display_name, update_channel_profile, set_business_username, update_commerce_settings, enable_local_storage, block_users and 43 more.
Can the 360dialog MCP server do things that cannot be undone?
- Yes. 4 tools can send, pay, publish or merge: mba_send_agent_event, mba_test_agent, mba_release_thread_control and mba_send_message.
What tools does the 360dialog MCP server have?
- 138 tools: 49 destructive, 4 irreversible, 16 write, 69 read. set_display_name, update_channel_profile, set_business_username, update_commerce_settings, enable_local_storage, block_users, unblock_users, update_company_details and 130 more.
Does the 360dialog MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the 360dialog MCP server send data to outside services?
- 13 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_client_documentation_page, check_number_eligibility, send_test_webhook_event, invite_user, sandbox_send_message, inbox_send_message and 7 more.
Has the 360dialog MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.