MCP server
Zendesk MCP server
A community MCP server that lets AI read Zendesk tickets, comments and attachments, create tickets and add comments.
- Community server
- CRM and sales
At a glance
- Maintained by
- reminia (community)
- Tools exposed
- 7 listed below
- Reviewed
- September 24, 2026
Why it matters
What it does and why it matters
Zendesk runs customer support for many companies. This community MCP server lets an assistant list and read tickets, read comments and attachments, create tickets, update them and add comments. That is enough to summarize tickets, draft replies and route work.
Zendesk has announced its own MCP server, but at review time we found no official developer documentation for it, so we list the most active community option and will update this page when the official one is documented.
The server uses a Zendesk API token, which carries the permissions of its user. Use an agent account limited to the needed groups. Adding public comments sends messages to customers, so we draft internal notes first and let agents send the final reply.
Use cases
Best business use cases
Ticket summaries
Routing
Trends
Ticket creation
Tools
Available tools
Tool names as published by the maintainer at review time. Versions change, so check the repository for the current list.
Read and write: Read and write on tickets and comments; Help Center articles exposed read-only as a resource.
-
get_ticketsFetch the latest tickets with paging and sorting.
-
get_ticketGet a ticket by ID.
-
get_ticket_commentsGet all comments on a ticket.
-
get_ticket_attachmentGet a ticket attachment.
-
create_ticketCreate a new ticket.
-
update_ticketUpdate ticket status, priority, assignee, tags and fields.
-
create_ticket_commentAdd a public or private comment to a ticket.
Workflows
Example workflows
Draft a reply
-
1
An agent opens a ticket.
-
2
The assistant reads the ticket and history.
-
3
It drafts a reply from help content.
-
4
It adds the draft as an internal note.
-
5
The agent edits and sends it.
Weekly issue themes
-
1
Ask for last week's tickets.
-
2
The assistant reads them.
-
3
It groups them by theme.
-
4
It highlights rising issues.
-
5
The support lead shares findings.
Prompts
Example prompts
“Summarize ticket 48213 and its history for me.”
“Draft a reply to this ticket as an internal note.”
“Group last week's tickets by topic and show the top five.”
Setup
Installation and configuration
Examples for Claude Desktop and Claude Code. Replace the placeholder values with your own keys, and store secrets outside version control.
Claude Desktop: claude_desktop_config.json
{
"mcpServers": {
"zendesk": {
"command": "uv",
"args": [
"--directory",
"/path/to/zendesk-mcp-server",
"run",
"zendesk"
]
}
}
}Claude Code: terminal
claude mcp add zendesk -- uv --directory /path/to/zendesk-mcp-server run zendesk- Local server: Python via uv from a cloned repo (uv run zendesk); Docker build also supported.
- Needs: OAuth with a public Zendesk OAuth client (PKCE). Set ZENDESK_SUBDOMAIN and ZENDESK_CLIENT_ID, then run uv run zendesk-auth once. API token auth still works but is deprecated..
Security
Security considerations
-
Right user, right access
Connect with a user whose CRM role fits the task, not an admin.
-
Start read-only
Begin with lookups. Add create and update actions one at a time.
-
Customer data
Tickets hold personal data. Limit groups and avoid copying data into other tools.
-
Audit changes
Review records changed through the assistant, especially in the first weeks.
Related servers
Servers that pair well with it
Intercom
Intercom's official hosted MCP server lets AI search conversations, contacts, companies and help articles, create articles and add notes.
Salesforce
Salesforce's official DX MCP server lets AI query data with SOQL, manage orgs and metadata, run tests and assign permission sets.
Slack
Slack's own hosted MCP server lets AI search messages, read channels and threads, look up people, draft or send messages and create canvases.
Keep exploring
Solutions and services that use it
Related services
View all related services- MCP integration Connect AI assistants to your CRM, files, databases and tools through Model Context Protocol servers, with safe permissions.
- CRM integration Connect your CRM to forms, email, billing and support so customer records stay complete without typing.
- AI agents AI that takes actions in your systems, such as qualifying leads or processing requests, with people checking the results.
- AI chatbots Website and messaging chatbots that answer common questions well and hand everything else to a person.
- Landing pages Single-purpose pages for a campaign, a launch or a product, built to load fast and test quickly.
- Voice AI Speech to text, call summaries and voice assistants that take bookings or answer routine calls.
Solutions
View all solutions- AI lead qualification Score, research and route every new inquiry so your team talks to the best leads first.
- AI sales research agent Short, sourced briefings on each prospect before a call, drafted by an AI agent from public information and your CRM.
- AI support agent An assistant that answers routine questions from your own content, checks orders and hands anything else to a person.
- Feedback analysis Read every review, survey and ticket, group them by theme and sentiment, and show what customers keep asking for.
- Internal help desk assistant An assistant in Slack or Teams that answers policy and how-to questions from your handbooks and opens tickets when needed.
- Approval workflows Requests, approvals and reminders in one place, with clear owners and deadlines instead of long email threads.
Industries
View all industries- Real estate Listing sites, lead handling, CRM automation and document workflows for agencies, brokers and developers.
- Hospitality and travel Booking sites, guest messaging, review analysis and multilingual content for hotels, tour operators and travel businesses.
- Professional services Client portals, proposal drafting, knowledge assistants and internal tools for consultancies, agencies and firms.
- Recruiting and staffing Candidate screening assistants, ATS integrations, interview notes and onboarding automation for recruiters and staffing firms.
Guides and articles
View all guides and articles- What are AI agents and how do businesses use them? What AI agents are, real business uses, the controls they need and how to start with one safely.
- How to connect AI to your CRM Connect AI assistants to HubSpot, Salesforce or other CRMs safely, with the tasks worth automating first.
- AI chatbot vs AI agent What separates a chatbot that answers from an agent that acts, and when you need each.
- What is the Model Context Protocol? A business guide to MCP: what it is, how MCP servers work, who supports it and how to start using it.
- How to build an AI workflow with MCP servers Plan, connect and test an AI workflow that uses MCP servers, from a single task to a reliable process.
AI models
View all ai models- ElevenLabs Eleven v3 ElevenLabs text-to-speech: the expressive Eleven v3 in 70+ languages, a real-time conversational version, and the low-latency Flash models, with voice cloning.
- GPT-4o mini TTS OpenAI's current text-to-speech model for turning text into natural spoken audio, at a low price level.
Glossary terms
View all glossary terms- Chatbot A chatbot is software that holds a conversation with people through text or voice, answering questions or completing simple tasks.
- Natural language processing Natural language processing is the field of AI that deals with understanding and generating human language, in text or speech.
- AI agent An AI agent is software that uses a language model to plan steps, call tools and act toward a goal, instead of only answering one question.
- CRM A CRM, or customer relationship management system, stores contacts, companies, deals and interactions so a team can manage its customer relationships in one place.
- MCP server An MCP server is a program or hosted service that exposes a system's data and actions as tools that AI assistants can use through the Model Context Protocol.
- Model Context Protocol The Model Context Protocol, or MCP, is an open standard for connecting AI assistants to external tools and data in a consistent way.
FAQ
Questions people ask us
Have a question that is not here? Ask us directly.
Zendesk has announced one, but we found no official developer docs at review time. This is a community server.
It can add comments. We recommend internal notes first and agent-sent replies.
A Zendesk subdomain, email and API token.