Jira MCP server

Jira MCP is a Go-based connector enabling AI assistants like Claude to interact with Atlassian Jira. This tool provides an interface for AI models to perform common Jira operations such as creating issues, adding comments, tracking sprints, and transitioning issues through workflows.

Installation

Several installation options are available:

Download from GitHub Releases

1. Visit the GitHub Releases page
2. Download the binary for your platform:
   • jira-mcp_linux_amd64 for Linux
   • jira-mcp_darwin_amd64 for macOS
   • jira-mcp_windows_amd64.exe for Windows
3. Make the binary executable (Linux/macOS):

   chmod +x jira-mcp_*
   

4. Move it to your PATH (Linux/macOS):

   sudo mv jira-mcp_* /usr/local/bin/jira-mcp
   

Install with Go

go install github.com/nguyenvanduocit/jira-mcp@latest

Using Docker

Pull pre-built image

docker pull ghcr.io/nguyenvanduocit/jira-mcp:latest

Or build locally

docker build -t jira-mcp .

Configuration

Authentication

The following environment variables are required:

ATLASSIAN_HOST=your_atlassian_host
ATLASSIAN_EMAIL=your_email
ATLASSIAN_TOKEN=your_token

You can set these:

• In the Docker run command (recommended)
• Through a .env file (use the -env flag)
• Directly in your shell environment

Setup with Claude and Cursor

Step 1: Install Jira MCP

Choose one of the installation methods above (Docker recommended).

Step 2: Configure Cursor

1. Open Cursor
2. Navigate to Settings > MCP > Add MCP Server
3. Add the following configuration:

Using Docker (Recommended)

{
  "mcpServers": {
    "jira": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e", "ATLASSIAN_HOST=your_jira_instance.atlassian.net",
        "-e", "[email protected]",
        "-e", "ATLASSIAN_TOKEN=your_atlassian_api_token",
        "ghcr.io/nguyenvanduocit/jira-mcp:latest"
      ]
    }
  }
}

Using Local Binary

{
  "mcpServers": {
    "jira": {
      "command": "/path/to/jira-mcp",
      "args": ["-env", "/path/to/.env"]
    }
  }
}

Step 3: Test the Connection

Verify the connection by asking Claude in Cursor:

@https://your_jira_instance.atlassian.net/browse/PROJ-123 get issue

Features and Capabilities

Jira MCP enables AI assistants to:

• Get detailed issue information
• Create, update, and search issues (including child issues)
• List all available issue types and statuses
• Add and retrieve comments
• Add worklogs to issues
• List and manage sprints
• Retrieve issue history and relationships
• Link issues and get related issues
• Transition issues through workflows

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.