Skip to main content
Glama

zendesk-mcp

A Model Context Protocol server that exposes Zendesk ticket read and write tools to Claude Code and other MCP clients.

What it does

  • Search, list (paginated), and fetch Zendesk tickets, comments, and attachments

  • Create new tickets and update existing ticket fields (including group, custom status, and tags)

  • Post public replies and internal notes

  • Set ticket status and assign tickets to agents

  • Browse and apply views and macros

  • Look up users, groups, organizations, and custom statuses

  • Read and write time-tracking entries

  • Format a ticket as a Markdown issue draft for handoff to a tracker (GitLab, GitHub, Jira)

  • Two MCP prompts (analyze-ticket, draft-ticket-response) for ticket analysis and response drafting

  • (Optional) Expose Zendesk Help Center articles as an MCP resource

  • (Optional) Read linked GitLab issues / MRs / commits via the Git-Zen Zendesk app

Related MCP server: Zendesk MCP Server

Prerequisites

  • Python 3.10 or newer

  • A Zendesk OAuth client. A Zendesk admin can create one at: https://<your-subdomain>.zendesk.com/admin/apps-integrations/apis/zendesk-api/oauth_clients Set the redirect URL to http://localhost:8787/callback and request scopes read write.

Install

Install into a project-local virtualenv. Using a venv keeps zendesk-mcp and its dependencies isolated from your system Python and from other projects, and is the recommended path for everything below.

From a clone of this repository:

python3 -m venv .venv
.venv/bin/pip install --upgrade pip
.venv/bin/pip install -e .

For development (also installs pytest):

.venv/bin/pip install -e ".[dev]"

Throughout this README, commands use the venv's binaries via .venv/bin/.... You can instead source .venv/bin/activate once per shell and drop the prefix — the result is the same.

OAuth setup

Run the interactive setup using the venv's Python:

.venv/bin/python -m zendesk_mcp setup

You will be prompted for:

  1. Your Zendesk subdomain (e.g. acme for acme.zendesk.com)

  2. The OAuth client ID created by your admin

  3. The OAuth client secret

  4. (Optional) A Git-Zen integration field ID — see Optional: Git-Zen integration

  5. (Optional) Whether to enable the Help Center knowledge base resource — see Optional: Help Center knowledge base

The setup opens a browser for the OAuth authorization step, then writes a token to ~/.config/zendesk-mcp/config.json (mode 0600).

If you have no browser, the URL is printed to the terminal — open it on any device, click Allow, and paste the resulting redirect URL back into the prompt.

Token expiry and refresh

Zendesk access tokens expire. OAuth clients created on or after 2026-04-30 get a 30-minute default lifetime; older clients issue non-expiring tokens unless an expiry is requested. Setup requests a 24-hour access token and a 90-day refresh token so the behaviour is the same either way, and the server renews the access token automatically — before it expires, and again if Zendesk rejects a token mid-request.

To make that possible, the config file also stores refresh_token, expires_at, client_id, and client_secret alongside the access token. Keep the file at mode 0600; it is the same trust level as the access token itself. If your OAuth client returns no refresh token, setup says so and the token is used as-is.

Re-run .venv/bin/python -m zendesk_mcp setup when:

  • the refresh token expires (90 days with no use), or

  • you revoke the OAuth grant in Zendesk.

In either case the tools return Zendesk authorization failed: ... Re-run: zendesk-mcp setup rather than failing opaquely.

Register with Claude Code

Register the MCP server using the venv's Python by absolute path. Claude Code launches the server in a fresh shell that does not inherit your activated venv, so the absolute path is required — pointing at a bare python here will fail to import zendesk_mcp.

ZENDESK_MCP_DIR="$(pwd)"   # run this from the repo root, after install
claude mcp add --scope user zendesk -- "$ZENDESK_MCP_DIR/.venv/bin/python" -m zendesk_mcp

Or just inline the absolute path you want:

claude mcp add --scope user zendesk -- /absolute/path/to/zendesk-mcp/.venv/bin/python -m zendesk_mcp

Then add the read tools to permissions.allow in ~/.claude/settings.json to avoid per-call prompts:

{
  "permissions": {
    "allow": [
      "mcp__zendesk__zendesk_get_ticket",
      "mcp__zendesk__zendesk_get_tickets",
      "mcp__zendesk__zendesk_get_comments",
      "mcp__zendesk__zendesk_list_attachments",
      "mcp__zendesk__zendesk_download_attachment",
      "mcp__zendesk__zendesk_search_tickets",
      "mcp__zendesk__zendesk_ticket_to_gitlab_context",
      "mcp__zendesk__zendesk_list_views",
      "mcp__zendesk__zendesk_get_view",
      "mcp__zendesk__zendesk_get_view_tickets",
      "mcp__zendesk__zendesk_list_macros",
      "mcp__zendesk__zendesk_preview_macro",
      "mcp__zendesk__zendesk_search_users",
      "mcp__zendesk__zendesk_get_groups",
      "mcp__zendesk__zendesk_get_group_users",
      "mcp__zendesk__zendesk_get_organization",
      "mcp__zendesk__zendesk_list_custom_statuses"
    ]
  }
}

Write tools (zendesk_post_comment, zendesk_post_internal_note, zendesk_set_ticket_status, zendesk_assign_ticket, zendesk_create_ticket, zendesk_update_ticket, zendesk_log_time, zendesk_add_tag, zendesk_remove_tag, zendesk_apply_macro) are intentionally not in the default allow-list — Claude will prompt you per call.

Restricting tools

Every tool is enabled by default. To narrow what a deployment can do, for example where ticket text is written by customers and the agent should not be able to reply to them, set either of these in ~/.config/zendesk-mcp/config.json or in the server's environment. Values from both are combined.

Config key

Environment variable

Effect

"read_only": true

ZENDESK_MCP_READ_ONLY=true

Registers no write tools (comments, notes, status, assignment, create/update, tags, macros, time logging)

"disabled_tools": ["zendesk_post_comment"]

ZENDESK_MCP_DISABLED_TOOLS=zendesk_post_comment,zendesk_apply_macro

Does not register the named tools

A disabled tool is never registered, so the model cannot see or call it. Names that match no tool are reported on stderr.

Tools

Tickets

Tools that return ticket records include channel, the channel the ticket arrived on (Zendesk's via.channel: web, email, api, ...), or null when Zendesk does not say. zendesk_get_ticket also returns custom_fields as a list of {id, value} pairs; a field that is not set on the ticket has a null value.

Tool

What it does

zendesk_search_tickets

Search tickets by status, priority, type, assignee, requester, tags, or keyword. Each result includes channel

zendesk_get_tickets

List tickets with pagination and sorting (page, per_page, sort_by, sort_order). Each ticket includes channel

zendesk_get_ticket

Get one ticket's metadata, including channel and custom_fields

zendesk_create_ticket

Create a new ticket (subject, description, optional priority/type/assignee_id/requester_id/tags/custom_fields)

zendesk_update_ticket

Update one or more fields on an existing ticket (status, priority, subject, type, assignee_id, requester_id, group_id, custom_status_id, tags, custom_fields, due_at)

zendesk_get_comments

Get the conversation thread on a ticket

zendesk_list_attachments

List attachments on a ticket

zendesk_download_attachment

Download an attachment to a local cache directory. The URL must be on your Zendesk host, and dest_dir must be inside the cache or a directory listed in attachment_allowed_dest_dirs in the config

zendesk_ticket_to_gitlab_context

Format a ticket and its conversation as a Markdown issue draft

zendesk_post_comment

Post a public reply on a ticket

zendesk_post_internal_note

Post an agent-only internal note on a ticket

zendesk_set_ticket_status

Set ticket status (new, open, pending, hold, solved, closed)

zendesk_assign_ticket

Assign a ticket to an agent by email or me

Tags

Tool

What it does

zendesk_add_tag

Add a tag to a ticket (idempotent)

zendesk_remove_tag

Remove a tag from a ticket (idempotent)

Views & Macros

Tool

What it does

zendesk_list_views

List all active views

zendesk_get_view

Get a view's filter conditions and execution settings

zendesk_get_view_tickets

Fetch tickets currently matching a view. Each ticket includes channel

zendesk_list_macros

List active macros with their actions

zendesk_preview_macro

Preview what changes a macro would make

zendesk_apply_macro

Apply a macro to a ticket (applies field changes and posts any comment)

Users, Groups & Organizations

Tool

What it does

zendesk_search_users

Find users by name or email

zendesk_get_groups

List all active groups

zendesk_get_group_users

List the members of a group

zendesk_get_organization

Fetch an organization including custom fields

zendesk_list_custom_statuses

List all custom ticket statuses and their IDs

Time tracking

Tool

What it does

zendesk_get_time_tracking

Read time-tracking entries for a ticket

zendesk_log_time

Log a time entry against a ticket

Git-Zen integration

Tool

What it does

zendesk_get_git_zen_links

(Git-Zen only) Get linked GitLab issues / MRs / commits for a ticket

Prompts

The server exposes two MCP prompts that some clients (e.g. Claude Desktop) surface as slash commands:

Prompt

Argument

What it does

analyze-ticket

ticket_id

Asks the model to fetch the ticket and produce a summary, status/timeline, and key interaction points

draft-ticket-response

ticket_id

Asks the model to fetch the ticket and draft a customer-facing response (with a confirmation step before posting)

Optional: Git-Zen integration

If your Zendesk instance uses the Git-Zen app, the zendesk_get_git_zen_links tool can read its custom-field payload. Find your instance's Git-Zen custom field ID under Admin → Tickets → Fields (it is a numeric ID), then either set it during .venv/bin/python -m zendesk_mcp setup or edit ~/.config/zendesk-mcp/config.json to add:

{
  "git_zen_field_id": 12345678901234
}

Without this configured, zendesk_get_git_zen_links returns a "not configured" message.

Optional: Help Center knowledge base

If your Zendesk instance has a published Help Center, you can expose its sections and articles as the zendesk://knowledge-base MCP resource. The resource returns a single JSON document covering all sections and articles, cached for one hour.

This is opt-in. Enable it by either answering "y" to the prompt during .venv/bin/python -m zendesk_mcp setup, or by adding the following to ~/.config/zendesk-mcp/config.json:

{
  "knowledge_base_enabled": true
}

When the flag is absent or false, the resource is not registered, keeping the server's resource list empty for instances without a Help Center.

Optional: downloading attachments outside the cache

zendesk_download_attachment writes files to ~/.cache/zendesk-mcp/attachments/<ticket_id>/ by default (configurable via attachment_cache_dir). The dest_dir argument can redirect a download elsewhere, but because attachment contents are controlled by whoever wrote the ticket, the tool only accepts a dest_dir inside the cache or inside a directory you have explicitly allowed. Add the directories you want to permit to ~/.config/zendesk-mcp/config.json:

{
  "attachment_allowed_dest_dirs": ["/home/me/work/support_bundles"]
}

Paths are resolved before the check, so .. segments and symlinks cannot escape an allowed directory. Any dest_dir outside the allowed set is refused before the download starts.

The download URL itself must be an https URL on <subdomain>.zendesk.com for your configured subdomain; the tool refuses anything else so the OAuth token is never sent to another host. Archives are limited to 10,000 entries and 256 MiB unpacked, and tar members that are not regular files or directories are skipped.

Development

python3 -m venv .venv
.venv/bin/pip install -e ".[dev]"
.venv/bin/pytest

Tests run on Python 3.10, 3.11, and 3.12 in CI (see .github/workflows/test.yml).

Releasing

Bump the version in pyproject.toml, mcpb/pyproject.toml (both the version and the zendesk-mcp== pin), mcpb/manifest.json, and server.json (both fields), then push a v* tag. That triggers .github/workflows/release.yml, which publishes to PyPI, packs the MCPB bundle, publishes server.json to the MCP Registry, and cuts the GitHub release.

Check the versions agree before tagging — the release fails fast otherwise:

python3 .github/scripts/check_versions.py 0.1.5

License

Apache-2.0

Available Tools

29 tools
zendesk_add_tagA

Add a tag to a Zendesk ticket. Idempotent: adding an existing tag returns the current tag list without modifying the ticket. Returns JSON with ticket_id and current tags.

Inputs: tag (required), ticket_id (required). Returns: result

zendesk_apply_macroA

Apply a macro to a Zendesk ticket. Fetches the macro preview, applies field changes, and posts any comment included in the macro. Returns JSON with id, status, tags, applied_changes, comment_added.

Inputs: macro_id (required), ticket_id (required). Returns: result

zendesk_assign_ticketA

Assign a Zendesk ticket to an agent by their email address. Pass 'me' as assignee_email to assign the ticket to yourself (the authenticated user).

Inputs: ticket_id (required), assignee_email (required). Returns: result

zendesk_create_ticketA

Create a new Zendesk ticket. subject and description are required. priority: low/normal/high/urgent. type: problem/incident/question/task. requester_id/assignee_id are user IDs (integers). custom_fields is a list of {id, value} dicts. Returns JSON of the created ticket.

Inputs: subject (required), description (required), tags, type, +4 more. Returns: result

zendesk_download_attachmentA

Download a Zendesk attachment. Obtain attachment_url and filename from zendesk_list_attachments. ticket_id is required for cache organization. Optional dest_dir overrides the default cache location; the file is written there and (for archives) extracted alongside it. Archives return a file list and unpack_dir — read individual files with your normal file tools. PDFs return up to ~500KB of extracted text. Images are base64-encoded.

Inputs: filename (required), ticket_id (required), attachment_url (required), dest_dir. Returns: result

zendesk_get_commentsA

Get all comments (public replies and internal notes) for a Zendesk ticket. Includes attachment metadata but does not download files.

Inputs: ticket_id (required). Returns: result

zendesk_get_groupsA

List all active Zendesk groups (excluding deleted). Returns JSON array of {id, name}.

Inputs: no named parameters. Returns: result

zendesk_get_group_usersB

List the members of a Zendesk group. Returns JSON array of {id, name, email}.

Inputs: group_id (required). Returns: result

zendesk_get_organizationB

Fetch a Zendesk organization including its custom fields and tags. Returns JSON with id, name, organization_fields, tags, created_at, updated_at.

Inputs: organization_id (required). Returns: result

zendesk_get_ticketA

Get a Zendesk ticket by ID. Returns ticket fields including status, priority, requester, assignee, tags, and description.

Inputs: ticket_id (required). Returns: result

zendesk_get_ticketsA

List Zendesk tickets with pagination. page: 1-based page number. per_page: max 100. sort_by: created_at, updated_at, priority, or status. sort_order: asc or desc. Returns tickets plus pagination metadata.

Inputs: page, sort_by, per_page, sort_order. Returns: result

zendesk_get_time_trackingA

Get time tracking data for a Zendesk ticket. Returns total time spent and time spent on the last update, in both seconds and human-readable format (e.g. '2h 15m').

Inputs: ticket_id (required). Returns: result

zendesk_get_viewA

Get a Zendesk view's definition including filter conditions and execution settings. Returns JSON with id, title, active, conditions, execution.

Inputs: view_id (required). Returns: result

zendesk_get_view_ticketsB

Get the tickets currently matching a Zendesk view. Returns JSON array of tickets with essential fields.

Inputs: view_id (required). Returns: result

zendesk_list_attachmentsA

List all attachments across all comments for a Zendesk ticket. Returns filename, content type, size, and download URL for each. Use zendesk_download_attachment to fetch file contents.

Inputs: ticket_id (required). Returns: result

zendesk_list_custom_statusesA

List all custom ticket statuses defined in Zendesk. Returns JSON array of {id, agent_label, end_user_label, status_category, active, default}. Use the id when setting custom_status_id on a ticket.

Inputs: no named parameters. Returns: result

zendesk_list_macrosA

List all active Zendesk macros with their actions. Returns JSON array of {id, title, description, actions: [{field, value}]}.

Inputs: no named parameters. Returns: result

zendesk_list_viewsA

List all active Zendesk views. Returns JSON array of {id, title}.

Inputs: no named parameters. Returns: result

zendesk_log_timeA

Log time spent on a Zendesk ticket. Adds seconds to the running total and records it as the last-update time. Returns logged amount and new total in seconds and human-readable format.

Inputs: seconds (required), ticket_id (required). Returns: result

zendesk_post_commentA

Post a public reply on a Zendesk ticket. The reply is visible to the requester. Use for customer-facing responses.

Inputs: body (required), ticket_id (required). Returns: result

zendesk_post_internal_noteA

Post an internal note on a Zendesk ticket. Internal notes are only visible to agents and are not sent to the requester.

Inputs: body (required), ticket_id (required). Returns: result

zendesk_preview_macroA

Preview the effect a macro would have (without applying it). Returns the result payload from Zendesk's apply preview endpoint.

Inputs: macro_id (required). Returns: result

zendesk_remove_tagA

Remove a tag from a Zendesk ticket. Idempotent: removing a tag that isn't present returns the current tag list without modifying the ticket. Returns JSON with ticket_id and current tags.

Inputs: tag (required), ticket_id (required). Returns: result

zendesk_search_ticketsA

Search Zendesk tickets by keyword and/or status. keywords: free-text search (e.g. 'login failure LDAP'). status: new, open, pending, hold, solved, closed — leave empty for all statuses. Returns id, subject, status, requester, assignee, and dates.

Inputs: limit, status, keywords. Returns: result

zendesk_search_usersA

Search Zendesk users by name or email. Returns JSON array of {id, name, email, role}.

Inputs: query (required). Returns: result

zendesk_set_ticket_statusB

Set the status of a Zendesk ticket. Valid statuses: new, open, pending, hold, solved, closed.

Inputs: status (required), ticket_id (required). Returns: result

zendesk_ticket_to_gitlab_contextA

Format a Zendesk ticket and its comments as an issue draft. Returns Markdown with ticket metadata, full conversation, and an empty Steps to Reproduce section. Use this output as the description when creating an issue in your tracker.

Inputs: ticket_id (required). Returns: result

zendesk_update_ticketA

Update one or more fields on a Zendesk ticket. Pass only the fields you want to change. status: new/open/pending/hold/solved/closed. priority: low/normal/high/urgent. type: problem/incident/question/task. assignee_id, requester_id, group_id, custom_status_id are integer IDs. due_at is ISO8601. Returns JSON of the refreshed ticket.

Inputs: ticket_id (required), tags, type, due_at, +8 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 29 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose, even where operations appear similar (e.g., get_ticket, get_tickets, search_tickets). Descriptions clarify when to use each, and there is no meaningful overlap that would cause an agent to select the wrong tool.

    Naming Consistency4/5

    All tools share the 'zendesk_' prefix and mostly follow a verb_noun pattern. There is some mixing between 'get_' and 'list_' for read operations, but overall the conventions are predictable and easy to follow.

    Tool Count2/5

    With 29 tools, this exceeds the 25-tool threshold for a 'too many' rating. While the scope is broad, the high count makes the surface feel heavy and increases selection complexity, even though each tool is well-scoped individually.

    Completeness4/5

    The server covers the full ticket lifecycle including comments, attachments, time tracking, views, and macros. Minor gaps exist such as lack of ticket deletion and user management, but core support workflows are well represented.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers