Skip to content

Zendesk MCP by usefulapi

io.usefulapi/zendeskusefulapi.iostreamable-httpv1.40.4Scanned

Read tickets, users, orgs, macros and satisfaction ratings; create, update and comment on tickets.

19 tools: 3 can delete or cancel things, 1 change things and 15 only read.

Tools: 3 delete, 0 irreversible, 1 write, 15 read.
  • Reads private data · 3
  • Reads text others write · 9
  • Can send data out · 1
  • 2 findings

The remote endpoint did not answer the last look. Remote posture

Anlyon alternative

4 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 Zendesk MCP by usefulapi can do

The Zendesk MCP by usefulapi is published by usefulapi.io, a domain the MCP Registry verified. It has 19 tools. It can delete or cancel things (3 tools: zendesk_create_ticket, zendesk_update_ticket and zendesk_add_ticket_comment) and create or change data (1 tool: zendesk_execute_view). 15 tools only read.

3 tools read private data (zendesk_list_ticket_comments, zendesk_current_user and zendesk_search_users); 9 tools bring in text other people can write (zendesk_search, zendesk_list_tickets, zendesk_get_ticket and 6 more); 1 tool can send data out of your system (zendesk_add_ticket_comment). 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 2 findings (credentials-mention and annotation-conflict). Each one comes with the text it matched.

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.

19 tools

Deletes or cancels 3Claude Code: deny
  • zendesk_add_ticket_commentMUTATING: add a comment to a ticket.Can send data outNo findings

    Why it is in this group

    • The name "zendesk_add_ticket_comment" says "add": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • outboundThe name "zendesk_add_ticket_comment" says "add" and "comment": it writes something other people read.
    Description, as the server wrote it
    MUTATING: add a comment to a ticket. `public` defaults to true (a reply visible to the requester); set it false for an internal agent note. Convenience over PUT /tickets/{id}.json.

    Annotations the server declares

    • title: Add ticket comment
    • destructiveHint: true
  • zendesk_create_ticketMUTATING: create a new support ticket.No findings

    Why it is in this group

    • The name "zendesk_create_ticket" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    MUTATING: create a new support ticket. `subject` and `comment_body` are required; the comment becomes the ticket's first message. Zendesk REST: POST /tickets.json.

    Annotations the server declares

    • title: Create ticket
    • destructiveHint: true
  • zendesk_update_ticketMUTATING: update an existing ticket.No findings

    Why it is in this group

    • The name "zendesk_update_ticket" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    MUTATING: update an existing ticket. Provide the ticket `id` plus at least one field to change (status, priority, assignee_id, group_id, type, tags, or a comment). Zendesk REST: PUT /tickets/{id}.json.

    Annotations the server declares

    • title: Update ticket
    • destructiveHint: true
Changes things 1Claude Code: ask
  • zendesk_execute_viewRun a saved view by id and return the matching tickets.1 finding

    Why it is in this group

    • The name "zendesk_execute_view" says "execute": 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 "zendesk_execute_view" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true}; The name "zendesk_execute_view" says "execute": a word for a change.

      What this check looks for
    Description, as the server wrote it
    Run a saved view by id and return the matching tickets. Zendesk REST: GET /views/{id}/execute.json.

    Annotations the server declares

    • title: Execute view
    • readOnlyHint: true
Only reads 15Show 15 read-only tools
  • zendesk_current_userReturn the currently authenticated user — a quick way to verify credentials and subdomain.Reads private data1 finding

    Why it is in this group

    • The description's first verb is "return": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "return" and "credential": it reads secrets.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...henticated user — a quick way to verify credentials and subdomain. Zendesk REST: GET /users..."

      What this check looks for
    Description, as the server wrote it
    Return the currently authenticated user — a quick way to verify credentials and subdomain. Zendesk REST: GET /users/me.json.

    Annotations the server declares

    • title: Current user (whoami)
    • readOnlyHint: true
  • zendesk_get_organizationFetch a single organization by id.No findings

    Why it is in this group

    • The name "zendesk_get_organization" says "get": a word for reading.
    Description, as the server wrote it
    Fetch a single organization by id. Zendesk REST: GET /organizations/{id}.json.

    Annotations the server declares

    • title: Get organization
    • readOnlyHint: true
  • zendesk_get_ticketFetch a single ticket by id.Reads text others writeNo findings

    Why it is in this group

    • The name "zendesk_get_ticket" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe name "zendesk_get_ticket" says "get" and "ticket": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "fetch" and "ticket": it reads issues, which other people can write.
    Description, as the server wrote it
    Fetch a single ticket by id. Zendesk REST: GET /tickets/{id}.json.

    Annotations the server declares

    • title: Get ticket
    • readOnlyHint: true
  • zendesk_get_ticket_metricsFetch SLA / response / resolution time metrics for a ticket.Reads text others writeNo findings

    Why it is in this group

    • The name "zendesk_get_ticket_metrics" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe name "zendesk_get_ticket_metrics" says "get" and "ticket": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "fetch" and "ticket": it reads issues, which other people can write.
    Description, as the server wrote it
    Fetch SLA / response / resolution time metrics for a ticket. Zendesk REST: GET /tickets/{id}/metrics.json.

    Annotations the server declares

    • title: Get ticket metrics
    • readOnlyHint: true
  • zendesk_get_userFetch a single user by id.No findings

    Why it is in this group

    • The name "zendesk_get_user" says "get": a word for reading.
    Description, as the server wrote it
    Fetch a single user by id. Zendesk REST: GET /users/{id}.json.

    Annotations the server declares

    • title: Get user
    • readOnlyHint: true
  • zendesk_list_groupsList agent groups.No findings

    Why it is in this group

    • The name "zendesk_list_groups" says "list": a word for reading.
    Description, as the server wrote it
    List agent groups. Zendesk REST: GET /groups.json.

    Annotations the server declares

    • title: List groups
    • readOnlyHint: true
  • zendesk_list_macrosList macros (reusable sets of ticket actions/replies agents apply).Reads text others writeNo findings

    Why it is in this group

    • The name "zendesk_list_macros" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "ticket": it reads issues, which other people can write.
    Description, as the server wrote it
    List macros (reusable sets of ticket actions/replies agents apply). Zendesk REST: GET /macros.json.

    Annotations the server declares

    • title: List macros
    • readOnlyHint: true
  • zendesk_list_organizationsList organizations (offset pagination).No findings

    Why it is in this group

    • The name "zendesk_list_organizations" says "list": a word for reading.
    Description, as the server wrote it
    List organizations (offset pagination). Zendesk REST: GET /organizations.json.

    Annotations the server declares

    • title: List organizations
    • readOnlyHint: true
  • zendesk_list_satisfaction_ratingsList customer satisfaction (CSAT) ratings, optionally filtered by score.No findings

    Why it is in this group

    • The name "zendesk_list_satisfaction_ratings" says "list": a word for reading.
    Description, as the server wrote it
    List customer satisfaction (CSAT) ratings, optionally filtered by score. Zendesk REST: GET /satisfaction_ratings.json.

    Annotations the server declares

    • title: List satisfaction ratings
    • readOnlyHint: true
  • zendesk_list_ticket_commentsList the comments (public replies and internal notes) on a ticket, oldest first.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "zendesk_list_ticket_comments" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "note": it reads notes.
    • untrusted-inputThe name "zendesk_list_ticket_comments" says "list" and "ticket": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "list" and "comment": it reads comments, which other people can write.
    Description, as the server wrote it
    List the comments (public replies and internal notes) on a ticket, oldest first. Zendesk REST: GET /tickets/{id}/comments.json.

    Annotations the server declares

    • title: List ticket comments
    • readOnlyHint: true
  • zendesk_list_ticket_fieldsList all standard and custom ticket fields — useful for discovering field ids/values before creating or updating tickets.Reads text others writeNo findings

    Why it is in this group

    • The name "zendesk_list_ticket_fields" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe name "zendesk_list_ticket_fields" says "list" and "ticket": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "list" and "ticket": it reads issues, which other people can write.
    Description, as the server wrote it
    List all standard and custom ticket fields — useful for discovering field ids/values before creating or updating tickets. Zendesk REST: GET /ticket_fields.json.

    Annotations the server declares

    • title: List ticket fields
    • readOnlyHint: true
  • zendesk_list_ticketsList recent tickets (offset pagination).Reads text others writeNo findings

    Why it is in this group

    • The name "zendesk_list_tickets" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe name "zendesk_list_tickets" says "list" and "ticket": it reads issues, which other people can write.
    • untrusted-inputThe description's first sentence says "list" and "ticket": it reads issues, which other people can write.
    Description, as the server wrote it
    List recent tickets (offset pagination). Zendesk REST: GET /tickets.json.

    Annotations the server declares

    • title: List tickets
    • readOnlyHint: true
  • zendesk_list_viewsList saved ticket views (curated ticket lists).Reads text others writeNo findings

    Why it is in this group

    • The name "zendesk_list_views" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "ticket": it reads issues, which other people can write.
    Description, as the server wrote it
    List saved ticket views (curated ticket lists). Use zendesk_execute_view to run one. Zendesk REST: GET /views.json.

    Annotations the server declares

    • title: List views
    • readOnlyHint: true
  • zendesk_search_usersFind users by name, email, phone, or other attributes.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "zendesk_search_users" says "search": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "find" and "email": it reads mail.
    • untrusted-inputThe description's first sentence says "find" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Find users by name, email, phone, or other attributes. Zendesk REST: GET /users/search.json.

    Annotations the server declares

    • title: Search users
    • 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.

27 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 data3
Reads files, mail, messages, databases, secrets, calendars or repositories.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__zendesk__zendesk_add_ticket_comment"
    ]
  }
}

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.

The remote endpoint did not answer the last look

Looked at Nov 20, 2026, 19:38 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

  1. 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: 4 to 0
    • Protocol version: 2025-06-18 to none
    • RFC 9728 protected resource metadata: https://zendesk.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
    • Authorization servers: https://zendesk.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.

1 warn1 info
  • The server marks "zendesk_execute_view" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The name "zendesk_execute_view" says "execute": a word for a change.

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...henticated user — a quick way to verify credentials and subdomain. Zendesk REST: GET /users..."

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. 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: 4 to 0
    • Protocol version: 2025-06-18 to none
    • RFC 9728 protected resource metadata: https://zendesk.usefulapi.io/.well-known/oauth-protected-resource/mcp to none
    • Authorization servers: https://zendesk.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 zendesk https://zendesk.usefulapi.io/mcp
claude mcp add --transport http zendesk https://zendesk.usefulapi.io/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__zendesk__zendesk_search",
      "mcp__zendesk__zendesk_list_tickets",
      "mcp__zendesk__zendesk_get_ticket",
      "mcp__zendesk__zendesk_list_ticket_comments",
      "mcp__zendesk__zendesk_current_user",
      "mcp__zendesk__zendesk_get_user",
      "mcp__zendesk__zendesk_search_users",
      "mcp__zendesk__zendesk_list_organizations",
      "mcp__zendesk__zendesk_get_organization",
      "mcp__zendesk__zendesk_list_groups",
      "mcp__zendesk__zendesk_list_views",
      "mcp__zendesk__zendesk_list_macros",
      "mcp__zendesk__zendesk_list_ticket_fields",
      "mcp__zendesk__zendesk_get_ticket_metrics",
      "mcp__zendesk__zendesk_list_satisfaction_ratings"
    ],
    "ask": [
      "mcp__zendesk__zendesk_execute_view"
    ],
    "deny": [
      "mcp__zendesk__zendesk_create_ticket",
      "mcp__zendesk__zendesk_update_ticket",
      "mcp__zendesk__zendesk_add_ticket_comment"
    ]
  }
}

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 zendesk. Review it before you use it.

Capability tags behind 11 rules
  • mcp__zendesk__zendesk_search untrusted-input
  • mcp__zendesk__zendesk_list_tickets untrusted-input
  • mcp__zendesk__zendesk_get_ticket untrusted-input
  • mcp__zendesk__zendesk_list_ticket_comments private-data, untrusted-input
  • mcp__zendesk__zendesk_current_user private-data
  • mcp__zendesk__zendesk_search_users private-data, untrusted-input
  • mcp__zendesk__zendesk_list_views untrusted-input
  • mcp__zendesk__zendesk_list_macros untrusted-input
  • mcp__zendesk__zendesk_list_ticket_fields untrusted-input
  • mcp__zendesk__zendesk_get_ticket_metrics untrusted-input
  • mcp__zendesk__zendesk_add_ticket_comment 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/zendesk/verify?hash=e2c30358b70271f87ebcf5f978132a254af0cd9c049b4665e9258167f4286257" | jq -e '.changed == false'

Pinned hash e2c30358b702, 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/zendesk/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.usefulapi/zendesk
[![Anlyon Radar](https://radar.anlyon.com/badge/io.usefulapi/zendesk.svg)](https://radar.anlyon.com/servers/io.usefulapi/zendesk)

Source: MCP Registry · repository. Synced Nov 18, 2026, 11:19 UTC.

Zendesk MCP by usefulapi: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Zendesk MCP by usefulapi safe?

No scan can promise that. What its definitions show: 19 tools, 4 of which can change, send or delete something, and 2 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 Zendesk MCP by usefulapi delete data?

Yes. 3 tools can delete, cancel or revoke something: zendesk_create_ticket, zendesk_update_ticket and zendesk_add_ticket_comment.

Can the Zendesk 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 Zendesk MCP by usefulapi have?

19 tools: 3 destructive, 1 write, 15 read. zendesk_create_ticket, zendesk_update_ticket, zendesk_add_ticket_comment, zendesk_execute_view, zendesk_search, zendesk_list_tickets, zendesk_get_ticket, zendesk_list_ticket_comments and 11 more.

Does the Zendesk MCP by usefulapi need sign-in or OAuth?

Its remote endpoint did not answer the last anonymous look.

Does the Zendesk 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): zendesk_add_ticket_comment.

Has the Zendesk MCP by usefulapi changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Oct 25, 2026.