HelpCrunch MCP by usefulapi
io.usefulapi/helpcrunchusefulapi.iostreamable-httpv1.40.4Scanned
Manage HelpCrunch chats, customers, agents and knowledge-base articles.
12 tools: 3 can delete or cancel things and 9 only read.
- Reads private data · 7
- Reads text others write · 7
- Can send data out · 1
- No findings
The remote endpoint did not answer the last look. Remote posture
Anlyon alternative
3 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 HelpCrunch MCP by usefulapi can do
The HelpCrunch MCP by usefulapi is published by usefulapi.io, a domain the MCP Registry verified. It has 12 tools. It can delete or cancel things (3 tools: helpcrunch_create_message, helpcrunch_update_chat_status and helpcrunch_assign_chat). 9 tools only read.
7 tools read private data (helpcrunch_list_chats, helpcrunch_get_chat, helpcrunch_get_chat_messages and 4 more); 7 tools bring in text other people can write (helpcrunch_list_chats, helpcrunch_get_chat, helpcrunch_get_chat_messages and 4 more); 1 tool can send data out of your system (helpcrunch_create_message). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Oct 25, 2026, version 1.40.4.
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.
12 tools
Deletes or cancels 3Claude Code: deny
helpcrunch_assign_chatASSIGNS (or unassigns) a LIVE chat to an agent.No findings
Why it is in this group
- The name "helpcrunch_assign_chat" says "assign": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it ASSIGNS (or unassigns) a LIVE chat to an agent. Pass `assignee` (agent id) to assign; omit it (or pass null) to unassign. HelpCrunch REST: PUT /chats/assignee.
Annotations the server declares
- title: Assign chat
- destructiveHint: true
helpcrunch_create_messagePOSTS a message into a LIVE chat — a customer-visible reply (type "message") or an internal private note (type "private").Can send data outNo findings
Why it is in this group
- The name "helpcrunch_create_message" says "create": a word for a change.
- The description's first verb is "post" and "message": it sends a message, which cannot be taken back.
- The server marks it destructive (destructiveHint: true).
What it can reach
- outboundThe name "helpcrunch_create_message" says "create" and "message": it writes something other people read.
Description, as the server wrote it POSTS a message into a LIVE chat — a customer-visible reply (type "message") or an internal private note (type "private"). Set `agent` (agent id) for agent messages; omit it for customer messages. HelpCrunch REST: POST /messages.
Annotations the server declares
- title: Create message
- destructiveHint: true
helpcrunch_update_chat_statusCHANGES the status of a LIVE chat (e.g.No findings
Why it is in this group
- The name "helpcrunch_update_chat_status" says "update": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it CHANGES the status of a LIVE chat (e.g. mark it opened, pending, on hold, or closed). HelpCrunch REST: PUT /chats/status.
Annotations the server declares
- title: Update chat status
- destructiveHint: true
Only reads 9Show 9 read-only tools
helpcrunch_get_chatGet a single chat (conversation) by id.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "helpcrunch_get_chat" says "get": a word for reading.
What it can reach
- private-dataThe name "helpcrunch_get_chat" says "get" and "chat": it reads messages.
- private-dataThe description's first sentence says "get" and "chat": it reads messages.
- untrusted-inputThe name "helpcrunch_get_chat" says "get" and "chat": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "get" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Get a single chat (conversation) by id. HelpCrunch REST: GET /chats/{id}.
Annotations the server declares
- title: Get chat
- readOnlyHint: true
helpcrunch_get_chat_messagesGet the messages of a chat (conversation), newest first (sorted by createdAt DESC).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "helpcrunch_get_chat_messages" says "get": a word for reading.
What it can reach
- private-dataThe name "helpcrunch_get_chat_messages" says "get" and "chat": it reads messages.
- private-dataThe description's first sentence says "get" and "message": it reads messages.
- untrusted-inputThe name "helpcrunch_get_chat_messages" says "get" and "chat": it reads messages, which other people can write.
- 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 the messages of a chat (conversation), newest first (sorted by createdAt DESC). Paginate with limit (max 100) / offset. HelpCrunch REST: GET /chats/{id}/messages.
Annotations the server declares
- title: Get chat messages
- readOnlyHint: true
helpcrunch_get_customerGet a single customer by id.No findings
Why it is in this group
- The name "helpcrunch_get_customer" says "get": a word for reading.
Description, as the server wrote it Get a single customer by id. HelpCrunch REST: GET /customers/{id}.
Annotations the server declares
- title: Get customer
- readOnlyHint: true
helpcrunch_get_organizationGet the organization's live-chat availability status — domain, whether the team is online (teamOnline), and whether chat is enabled (chatEnabled).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "helpcrunch_get_organization" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "get" and "chat": it reads messages, which other people can write.
Description, as the server wrote it Get the organization's live-chat availability status — domain, whether the team is online (teamOnline), and whether chat is enabled (chatEnabled). HelpCrunch REST: GET /organization.
Annotations the server declares
- title: Get organization
- readOnlyHint: true
helpcrunch_list_agentsList agents (support staff / operators) in the account, with role and email.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "helpcrunch_list_agents" 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 agents (support staff / operators) in the account, with role and email. Paginate with limit/offset. HelpCrunch REST: GET /agents.
Annotations the server declares
- title: List agents
- readOnlyHint: true
helpcrunch_list_applicationsList applications configured in the account — web chat widgets, iOS/Android apps, and social integrations (id, name, displayName, active, type).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "helpcrunch_list_applications" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "list" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it List applications configured in the account — web chat widgets, iOS/Android apps, and social integrations (id, name, displayName, active, type). HelpCrunch REST: GET /applications.
Annotations the server declares
- title: List applications
- readOnlyHint: true
helpcrunch_list_chatsList / search chats (conversations).Reads private dataReads text others writeNo findings
Why it is in this group
- The name "helpcrunch_list_chats" says "list": a word for reading.
What it can reach
- private-dataThe name "helpcrunch_list_chats" says "list" and "chat": it reads messages.
- private-dataThe description's first sentence says "list" and "chat": it reads messages.
- untrusted-inputThe name "helpcrunch_list_chats" says "list" and "chat": it reads messages, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "chat": it reads messages, which other people can write.
Description, as the server wrote it List / search chats (conversations). Optionally filter with a single field/operator/value clause (comparison AND), sort (e.g. chats.createdAt) with order, and paginate with limit/offset. HelpCrunch REST: POST /chats/search.
Annotations the server declares
- title: List chats
- readOnlyHint: true
helpcrunch_list_customersList / search customers (people who chatted in).No findings
Why it is in this group
- The name "helpcrunch_list_customers" says "list": a word for reading.
Description, as the server wrote it List / search customers (people who chatted in). Optionally filter with a single field/operator/value clause (comparison AND), sort (e.g. customers.firstSeen, customers.lastSeen) with order, and paginate with limit/offset. HelpCrunch REST: POST /customers/search.
Annotations the server declares
- title: List customers
- readOnlyHint: true
helpcrunch_list_departmentsList departments (groups of agents that chats can be routed to), each with its agents.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "helpcrunch_list_departments" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "list" and "chat": it reads messages.
- untrusted-inputThe description's first sentence says "list" and "chat": it reads messages, which other people can write.
Description, as the server wrote it List departments (groups of agents that chats can be routed to), each with its agents. Paginate with limit/offset. HelpCrunch REST: GET /departments.
Annotations the server declares
- title: List departments
- readOnlyHint: 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.
49 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.
- Reads private data7
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__helpcrunch__helpcrunch_create_message"
]
}
}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 20, 2026, 19:36 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- no
- HTTP status of an anonymous initialize
- not observed
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: The server redirected a POST to a different request.
Posture changes
- Oct 29, 2026
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://helpcrunch.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://helpcrunch.usefulapi.io to none
- Dynamic client registration: yes to not observed
- Client ID metadata documents: no to not observed
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Reachable: yes -> no; HTTP status of an anonymous initialize: 200 -> none; tools/list served without credentials: yes -> no (and 6 more).View diff
- Reachable: yes to no
- HTTP status of an anonymous initialize: 200 to none
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
- RFC 9728 protected resource metadata: https://helpcrunch.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
- Authorization servers: https://helpcrunch.usefulapi.io to none
- Dynamic client registration: yes to not observed
- Client ID metadata documents: no to not observed
Install
Pinned to version 1.40.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http helpcrunch https://helpcrunch.usefulapi.io/mcpclaude mcp add --transport http helpcrunch https://helpcrunch.usefulapi.io/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__helpcrunch__helpcrunch_list_customers",
"mcp__helpcrunch__helpcrunch_get_customer",
"mcp__helpcrunch__helpcrunch_list_chats",
"mcp__helpcrunch__helpcrunch_get_chat",
"mcp__helpcrunch__helpcrunch_get_chat_messages",
"mcp__helpcrunch__helpcrunch_list_agents",
"mcp__helpcrunch__helpcrunch_list_departments",
"mcp__helpcrunch__helpcrunch_list_applications",
"mcp__helpcrunch__helpcrunch_get_organization"
],
"ask": [],
"deny": [
"mcp__helpcrunch__helpcrunch_create_message",
"mcp__helpcrunch__helpcrunch_update_chat_status",
"mcp__helpcrunch__helpcrunch_assign_chat"
]
}
}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 helpcrunch. Review it before you use it.
Capability tags behind 8 rules
- mcp__helpcrunch__helpcrunch_list_chats private-data, untrusted-input
- mcp__helpcrunch__helpcrunch_get_chat private-data, untrusted-input
- mcp__helpcrunch__helpcrunch_get_chat_messages private-data, untrusted-input
- mcp__helpcrunch__helpcrunch_list_agents private-data, untrusted-input
- mcp__helpcrunch__helpcrunch_list_departments private-data, untrusted-input
- mcp__helpcrunch__helpcrunch_list_applications private-data, untrusted-input
- mcp__helpcrunch__helpcrunch_get_organization private-data, untrusted-input
- mcp__helpcrunch__helpcrunch_create_message outbound
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/io.usefulapi/helpcrunch/verify?hash=b590755a07587d0da37c01836de2219ed194b5dad4363f89779ced6b5f2be9dc" | jq -e '.changed == false'Pinned hash b590755a0758, from Oct 25, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.usefulapi/helpcrunch/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.usefulapi/helpcrunch)Source: MCP Registry · repository. Synced Nov 18, 2026, 11:18 UTC.
HelpCrunch MCP by usefulapi: questions and answers
Answered from the scan above, not from the publisher's description.
Is the HelpCrunch MCP by usefulapi safe?
- No scan can promise that. What its definitions show: 12 tools, 3 of which can change, send or delete something, and 0 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 HelpCrunch MCP by usefulapi delete data?
- Yes. 3 tools can delete, cancel or revoke something: helpcrunch_create_message, helpcrunch_update_chat_status and helpcrunch_assign_chat.
Can the HelpCrunch MCP by usefulapi 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 HelpCrunch MCP by usefulapi have?
- 12 tools: 3 destructive, 9 read. helpcrunch_create_message, helpcrunch_update_chat_status, helpcrunch_assign_chat, helpcrunch_list_customers, helpcrunch_get_customer, helpcrunch_list_chats, helpcrunch_get_chat, helpcrunch_get_chat_messages and 4 more.
Does the HelpCrunch MCP by usefulapi need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the HelpCrunch MCP by usefulapi send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): helpcrunch_create_message.
Has the HelpCrunch MCP by usefulapi changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Oct 25, 2026.