Summary
This is a gateway-based server that connects Claude to your Zendesk account through OAuth. You get five main tools: list and search tickets, fetch individual tickets by ID, and query users and user details. It's hosted by Pipeworx, so there's no local setup. You can either call the tools directly (zd_list_tickets, zd_search_tickets, etc.) or use their ask_pipeworx interface to query in natural language and let the gateway route to the right endpoint. Useful when you're building support workflows, want to surface ticket context during conversations, or need to pull user data without switching to the Zendesk UI.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Tools
Public tool metadata for what this MCP can expose to an agent.
16 tools
ZENDESK_COUNT_ZENDESK_ORGANIZATIONSCount the number of organizations in Zendesk.
Count the number of organizations in Zendesk.
No parameter schema in public metadata yet.
ZENDESK_CREATE_ZENDESK_ORGANIZATIONTool to create a Zendesk organization. Use when you need to group end users under a shared company profile. Use after confirming the organization name is unique.2 params
Tool to create a Zendesk organization. Use when you need to group end users under a shared company profile. Use after confirming the organization name is unique.
Parameters* required
external_idstringOptional unique external identifier for this organization. Comparison is case-insensitive; use to sync with external systems.
namestringUnique organization name. Leading/trailing whitespace is trimmed by Zendesk.
ZENDESK_CREATE_ZENDESK_TICKETCreate a ticket in Zendesk.5 params
Create a ticket in Zendesk.
Parameters* required
descriptionstringLong-form description / steps to reproduce.
prioritystringZendesk priority. Must be one of: 'urgent', 'high', 'normal', 'low'.one of
urgent · high · normal · lowdefault: normalrequester_emailstringEmail of the requester. Must accompany `requester_name`.
requester_namestringName of the requester. If you supply this, you MUST also supply `requester_email`. Leave both blank to default to the authenticated user.
subjectstringShort summary of the issue. Keep it concise (e.g. 'Cannot log in').
ZENDESK_CREATE_ZENDESK_USERTool to create a new user in Zendesk. Use when you need to onboard a user with specific details.2 params
Tool to create a new user in Zendesk. Use when you need to onboard a user with specific details.
Parameters* required
skip_verify_emailbooleanIf true, do not send a verification email upon creationdefault: false
userobjectUser object containing all attributes to create
ZENDESK_DELETE_ZENDESK_ORGANIZATIONDelete an organization in Zendesk.1 params
Delete an organization in Zendesk.
Parameters* required
organization_idstringID of the organization to delete
ZENDESK_DELETE_ZENDESK_TICKETDelete a ticket in Zendesk.1 params
Delete a ticket in Zendesk.
Parameters* required
ticket_idintegerID of the ticket to delete
ZENDESK_DESTROY_MANY_ORGANIZATIONSTool to bulk delete Zendesk organizations. Use when cleaning up test data or removing obsolete organizations in one call. Returns a job_status payload to track progress.2 params
Tool to bulk delete Zendesk organizations. Use when cleaning up test data or removing obsolete organizations in one call. Returns a job_status payload to track progress.
Parameters* required
external_idsstringComma-separated list of Zendesk external organization IDs to delete (max 100). Required if ids is not provided.
idsstringComma-separated list of Zendesk organization IDs to delete (max 100). Required if external_ids is not provided.
ZENDESK_GET_ABOUT_MEGet information about the owner account in Zendesk.
Get information about the owner account in Zendesk.
No parameter schema in public metadata yet.
ZENDESK_GET_ALL_ZENDESK_ORGANIZATIONSGet all organizations in Zendesk.
Get all organizations in Zendesk.
No parameter schema in public metadata yet.
ZENDESK_GET_ZENDESK_ORGANIZATIONGet information about a specific organization in Zendesk.1 params
Get information about a specific organization in Zendesk.
Parameters* required
organization_idintegerNumeric ID of the organization to retrieve (e.g. 123456).
ZENDESK_GET_ZENDESK_TICKET_BY_IDGet ticket details from Zendesk.1 params
Get ticket details from Zendesk.
Parameters* required
ticket_idintegerID of the ticket to get details for.
ZENDESK_LIST_ZENDESK_TICKETSList Zendesk tickets with pagination and filtering.5 params
List Zendesk tickets with pagination and filtering.
Parameters* required
external_idstringFilter tickets by external ID
pageintegerPage number for offset pagination (starts at 1)
per_pageintegerNumber of tickets per page (max 100)
sort_bystringField to sort by: 'assignee', 'assignee.name', 'created_at', 'group', 'id', 'requester', 'requester.name', 'status', 'subject', 'updated_at'
sort_orderstringSort order: 'asc' or 'desc'one of
asc · descZENDESK_REPLY_ZENDESK_TICKETAction to reply to a Zendesk ticket by adding a comment.3 params
Action to reply to a Zendesk ticket by adding a comment.
Parameters* required
bodystringComment contentdefault:
publicbooleanWhether the comment is public or internaldefault: true
ticket_idintegerID of the ticket to reply to
ZENDESK_SEARCH_ZENDESK_USERSTool to search Zendesk users by email or name. Use after confirming user identity before ticket creation.4 params
Tool to search Zendesk users by email or name. Use after confirming user identity before ticket creation.
Parameters* required
emailstringEmail address to search for. Exact match (e.g., 'jdoe@example.com').
namestringFull or partial name to search for. For phrase searches, enclose in quotes.
pageintegerPage number for offset pagination (starts at 1).
per_pageintegerNumber of users per page (max 100).
ZENDESK_UPDATE_ZENDESK_ORGANIZATIONUpdate an organization in Zendesk.2 params
Update an organization in Zendesk.
Parameters* required
dataobjectNew data for the organization
organization_idintegerID of the organization to update
ZENDESK_UPDATE_ZENDESK_TICKETTool to update a ticket in Zendesk. Use when you need to modify ticket fields like status, priority, or subject after confirming the ticket ID.21 params
Tool to update a ticket in Zendesk. Use when you need to modify ticket fields like status, priority, or subject after confirming the ticket ID.
Parameters* required
additional_collaboratorsarrayAdd collaborators without removing existing ones.
collaborator_idsarrayCollaborator user IDs to set (replaces existing).
collaboratorsarrayCollaborators to set (replaces existing). Accepts user IDs, emails, or {name, email} objects.
comment_author_idintegerAuthor ID for the comment, if different from the authenticated user.
comment_bodystringText body of the comment to add.
comment_html_bodystringHTML body of the comment to add.
comment_publicbooleanWhether the added comment is public (visible to requester) or internal.
comment_uploadsarrayUpload tokens to attach files to the comment.
custom_fieldsarrayList of custom field values. Each item: {id: number, value: any}.
dataobjectOptional raw ticket update object. Provide this to send fields under the 'ticket' wrapper directly. Alternatively, use the un-nested fields above.
due_atstringDue date/time for task-type tickets (ISO 8601).
email_ccsarrayEmail CCs to add/remove. Each object includes user_id or user_email, optional user_name, and action ('put'|'delete').
followersarrayFollowers to add/remove. Each object should include user_id or user_email, with optional action ('put'|'delete').
metadataobjectCustom metadata to attach to this update's audit (approximately up to 1 KB).
prioritystringTicket priority. Allowed values: urgent, high, normal, low.one of
urgent · high · normal · lowsafe_updatebooleanEnable optimistic locking to prevent overwrites during collisions.
statusstringTicket status to set. If your account uses custom statuses, use custom_status_id via other endpoints.
subjectstringTicket subject/title to set during update.
tagsarrayTags to set on the ticket. Using tags here replaces all existing tags.
ticket_idintegerID of the ticket to update.
+1 more parameters. See the server's own documentation for the full schema.
mcp-zendesk
Zendesk MCP Pack — tickets, users, organizations via OAuth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
Tools
| Tool | Description |
|---|---|
zd_list_tickets | List Zendesk support tickets for the connected account, sortable by created_at, updated_at, priority, or status. Returns ticket IDs, subjects, statuses, and metadata. Supports pagination via page. |
zd_get_ticket | Get a Zendesk ticket by ID. |
zd_search_tickets | Search Zendesk tickets with a query string. |
zd_list_users | List all Zendesk users (agents and end-users) in the connected account. Returns user IDs, names, emails, and roles. Supports pagination via page number. |
zd_get_user | Get a Zendesk user by ID. |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"zendesk": {
"url": "https://gateway.pipeworx.io/zendesk/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/zendesk/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Zendesk data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →