Zendesk MCP server for AI agents

This MCP server integrates with Zendesk to provide tools and specialized prompts for ticket management and customer support automation. It enables retrieval and management of Zendesk tickets, offers ticket analysis capabilities, and provides access to Zendesk Help Center articles as a knowledge base.

Installation

Prerequisites

Python with uv package manager installed
Zendesk account credentials

Step-by-Step Installation

Clone the repository to your local machine
Install the package:
```
uv venv && uv pip install -e .
```
Or use the shorthand command:
```
uv build
```
Set up your Zendesk credentials in an environment file:
- Create a .env file in the root directory of the project
- Add your Zendesk credentials following the format in .env.example

Claude Desktop Configuration

Configure the MCP server in Claude desktop by adding the following to your Claude configuration:

{
  "mcpServers": {
      "zendesk": {
          "command": "uv",
          "args": [
              "--directory",
              "/path/to/zendesk-mcp-server",
              "run",
              "zendesk"
          ]
      }
  }
}

Make sure to replace /path/to/zendesk-mcp-server with the actual path to your installation directory.

Usage

Available Resources

Knowledge Base Access: Use zendesk://knowledge-base to access all Help Center articles.

Specialized Prompts

The MCP server provides two specialized prompts:

analyze-ticket

This prompt helps you analyze a Zendesk ticket in detail, providing insights and information about the ticket content.

draft-ticket-response

Use this prompt to generate draft responses to Zendesk tickets, saving time and ensuring consistent communication.

Available Tools

The server provides three main tools for ticket management:

get_ticket

Retrieves a Zendesk ticket by its ID.

Input parameters:

ticket_id (integer): The ID of the ticket to retrieve

Example usage:

Tool: get_ticket
Input: {"ticket_id": 12345}

get_ticket_comments

Retrieves all comments for a Zendesk ticket by its ID.

Input parameters:

ticket_id (integer): The ID of the ticket to get comments for

Example usage:

Tool: get_ticket_comments
Input: {"ticket_id": 12345}

create_ticket_comment

Creates a new comment on an existing Zendesk ticket.

Input parameters:

ticket_id (integer): The ID of the ticket to comment on
comment (string): The comment text/content to add
public (boolean, optional): Whether the comment should be public (defaults to true)

Example usage:

Tool: create_ticket_comment
Input: {
  "ticket_id": 12345,
  "comment": "Thank you for your patience. We're working on resolving your issue.",
  "public": true
}

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.