Assistable MCP server
ai.assistable/assistableassistable.aistreamable-httpv1.0.0Scanned
Give any AI agent a phone: make and answer calls, get through phone menus, and send texts.
16 tools: 2 can delete or cancel things, 5 change things and 9 only read.
- Reads private data · 3
- Reads text others write · 10
- Can send data out · 2
- 1 finding
Tools listed without sign-in. Remote posture
Anlyon alternative
7 of these tools change something. Run those as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the Assistable MCP server can do
The Assistable MCP server is published by assistable.ai, a domain the MCP Registry verified. It has 16 tools. It can delete or cancel things (2 tools: assistants_archive and tools_delete) and create or change data (5 tools: assistants_create, assistants_update, tools_create_custom, tools_update and 1 more). 9 tools only read.
3 tools read private data (contacts_list, contacts_get and conversations_list); 10 tools bring in text other people can write (search_tools, assistants_list, assistants_get and 7 more); 2 tools can send data out of your system (tools_create_custom and tools_update). 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 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 10, 2026, version 1.0.0.
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.
16 tools
Deletes or cancels 2Claude Code: deny
assistants_archiveArchive (soft-delete) an assistant.No findings
Why it is in this group
- The name "assistants_archive" says "archive": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Archive (soft-delete) an assistant.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
tools_deleteSoft-delete a custom tool.No findings
Why it is in this group
- The name "tools_delete" says "delete": a word for removing or ending something.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Soft-delete a custom tool.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
Changes things 5Claude Code: ask
assistants_createCreate an assistant.No findings
Why it is in this group
- The name "assistants_create" says "create": a word for a change.
Description, as the server wrote it Create an assistant. Required: subAccountId, name. Optional config blocks (llmConfig, voiceConfig, chatConfig) mirror the dashboard create dialog. voice_settings configures call greeting mode, opening messages, and voicemail behavior; platform_tools attaches platform-catalog tools (declarative full-replace — see the field description).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
assistants_updatePatch an assistant.No findings
Why it is in this group
- The name "assistants_update" says "update": a word for a change.
Description, as the server wrote it Patch an assistant. Only supplied fields change; nested config blocks are upserted. voice_settings updates call greeting mode, opening messages, and voicemail behavior; platform_tools declaratively replaces the attached platform-catalog tools (an empty array detaches all — see the field description).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
calls_getFetch a call (status, recording, transcript) by ID.Reads text others write1 finding
Why it is in this group
- The name "calls_get" says "call": a word for a change.
- 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.
Findings
- Warn
The server marks "calls_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "calls_get" says "call": a word for a change.
Description, as the server wrote it Fetch a call (status, recording, transcript) by ID.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
tools_create_customCreate a custom tool (toolType=CUSTOM).Can send data outNo findings
Why it is in this group
- The name "tools_create_custom" says "create": a word for a change.
What it can reach
- 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 Create a custom tool (toolType=CUSTOM). Name must match /^[a-zA-Z0-9_-]+$/ and be unique in the subaccount.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
tools_updatePatch a custom tool.Can send data outNo findings
Why it is in this group
- The name "tools_update" says "update": a word for a change.
What it can reach
- 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 Patch a custom tool. Supplying parameters/headers replaces those rows; omit to leave them.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
Only reads 9Show 9 read-only tools
appointments_listList appointments in a subaccount within an optional date range.Reads text others writeNo findings
Why it is in this group
- The name "appointments_list" 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 appointments in a subaccount within an optional date range.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
assistants_getFetch an assistant's full configuration by ID.Reads text others writeNo findings
Why it is in this group
- The name "assistants_get" 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 Fetch an assistant's full configuration by ID. The response includes voice_settings (greeting mode, opening messages, voicemail) and platform_tools (attached platform-catalog tool names).
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
assistants_listList assistants in a subaccount (excludes archived by default).Reads text others writeNo findings
Why it is in this group
- The name "assistants_list" 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 assistants in a subaccount (excludes archived by default). Note: voice_settings and platform_tools are returned only by assistants_get, not in the list.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contacts_getFetch a contact by ID.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "contacts_get" says "get": a word for reading.
What it can reach
- private-dataThe name "contacts_get" says "get" and "contact": it reads contacts.
- private-dataThe description's first sentence says "fetch" and "contact": it reads contacts.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Fetch a contact by ID.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
contacts_listList contacts in a subaccount.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "contacts_list" says "list": a word for reading.
What it can reach
- private-dataThe name "contacts_list" says "list" and "contact": it reads contacts.
- private-dataThe description's first sentence says "list" and "contact": it reads contacts.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List contacts in a subaccount. meta.total is the number of matching contacts, so use it to answer how many contacts there are.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
conversations_listList conversations in a subaccount.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "conversations_list" says "list": a word for reading.
What it can reach
- private-dataThe name "conversations_list" says "list" and "conversation": it reads messages.
- private-dataThe description's first sentence says "list" and "conversation": it reads messages.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "conversations_list" says "list" and "conversation": it reads messages, 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 in a subaccount.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
search_toolsSearch Assistable's registered MCP tools by the task the user wants to do.Reads text others writeNo findings
Why it is in this group
- The name "search_tools" says "search": 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 Search Assistable's registered MCP tools by the task the user wants to do. Returns up to 5 exact tool definitions with JSON input schemas and annotations. Use this first when you need to choose a tool; the result is not authorization to call it.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
tools_getFetch a tool's full configuration.Reads text others writeNo findings
Why it is in this group
- The name "tools_get" 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 Fetch a tool's full configuration.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
tools_listList tools visible to a subaccount.Reads text others writeNo findings
Why it is in this group
- The name "tools_list" 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 tools visible to a subaccount. Pass includePrebuilt=false for only custom tools.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
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.
60 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write10
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__assistable__tools_create_custom",
"mcp__assistable__tools_update"
]
}
}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 19, 2026, 17:23 UTC, unchanged since Nov 5, 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
- 7
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://api.assistable.ai/.well-known/oauth-protected-resource
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 7 tools that change things (2 destructive, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.assistable.ai/mcp: tools/list returned 16 tools to an anonymous client, including assistants_archive (destructive), tools_delete (destructive), assistants_create (write), assistants_update (write), tools_create_custom (write) and 2 more
Posture changes
- Nov 5, 2026
- Tools that change things, listed without credentials: 9 to 7
Findings
Matches of fixed checks, with the text they matched.
- Warncalls_get
The server marks "calls_get" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "calls_get" says "call": a word for a change.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 removed.−2 removedView diff
- Removed:assistable_connect
- Removed:assistable_connect_finish
PostureRemote posture changed. Tools that change things, listed without credentials: 9 -> 7.View diff
- Tools that change things, listed without credentials: 9 to 7
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http assistable https://api.assistable.ai/mcpclaude mcp add --transport http assistable https://api.assistable.ai/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__assistable__search_tools",
"mcp__assistable__assistants_list",
"mcp__assistable__assistants_get",
"mcp__assistable__tools_list",
"mcp__assistable__tools_get",
"mcp__assistable__contacts_list",
"mcp__assistable__contacts_get",
"mcp__assistable__conversations_list",
"mcp__assistable__appointments_list"
],
"ask": [
"mcp__assistable__assistants_create",
"mcp__assistable__assistants_update",
"mcp__assistable__tools_create_custom",
"mcp__assistable__tools_update",
"mcp__assistable__calls_get"
],
"deny": [
"mcp__assistable__assistants_archive",
"mcp__assistable__tools_delete"
]
}
}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 assistable. Review it before you use it.
Capability tags behind 12 rules
- mcp__assistable__search_tools untrusted-input
- mcp__assistable__assistants_list untrusted-input
- mcp__assistable__assistants_get untrusted-input
- mcp__assistable__tools_list untrusted-input
- mcp__assistable__tools_get untrusted-input
- mcp__assistable__tools_create_custom outbound
- mcp__assistable__tools_update outbound
- mcp__assistable__contacts_list private-data, untrusted-input
- mcp__assistable__contacts_get private-data, untrusted-input
- mcp__assistable__conversations_list private-data, untrusted-input
- mcp__assistable__appointments_list untrusted-input
- mcp__assistable__calls_get 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/ai.assistable/assistable/verify?hash=14aac9afebc7da1c284047abc4379bb383c618a6e24fe4ebea89c58d993368f7" | jq -e '.changed == false'Pinned hash 14aac9afebc7, from Nov 10, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.assistable/assistable/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.assistable/assistable)Source: MCP Registry. Synced Oct 28, 2026, 19:17 UTC.
Assistable MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Assistable MCP server safe?
- No scan can promise that. What its definitions show: 16 tools, 7 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Assistable MCP server delete data?
- Yes. 2 tools can delete, cancel or revoke something: assistants_archive and tools_delete.
Can the Assistable MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Assistable MCP server have?
- 16 tools: 2 destructive, 5 write, 9 read. assistants_archive, tools_delete, assistants_create, assistants_update, tools_create_custom, tools_update, calls_get, search_tools and 8 more.
Does the Assistable MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Assistable MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): tools_create_custom and tools_update.
Has the Assistable MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.