Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

jira-mcp

MCP.Pizza Chef: nguyenvanduocit

jira-mcp is a Go-based MCP server that connects AI assistants like Claude to Atlassian Jira, enabling them to perform issue management, sprint planning, and workflow transitions. It provides detailed access to Jira data such as issues, comments, worklogs, sprints, and issue relationships, allowing AI models to interact with Jira in real time and automate common project management tasks efficiently.

Use This MCP server To

Retrieve detailed Jira issue information for analysis Create and update Jira issues via AI commands Search Jira issues including child issues List all Jira issue types and statuses Add and retrieve comments on Jira issues Add worklogs to Jira issues List and manage Jira sprints Retrieve issue history and relationships Link related Jira issues Transition Jira issues through workflows

README

Jira MCP

A Go-based MCP (Model Control Protocol) connector for Jira that enables AI assistants like Claude to interact with Atlassian Jira. This tool provides a seamless interface for AI models to perform common Jira operations.

Features

  • 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

Installation

Requirements: Go 1.20+ (for building from source)

There are several ways to install Jira MCP:

Option 1: 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

Option 2: Go install

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

Option 3: Docker

Using Docker directly
  1. Pull the pre-built image from GitHub Container Registry:

    docker pull ghcr.io/nguyenvanduocit/jira-mcp:latest
  2. Or build the Docker image locally:

    docker build -t jira-mcp .

Configuration

Environment Variables

The following environment variables are required for authentication:

ATLASSIAN_HOST=your_atlassian_host
ATLASSIAN_EMAIL=your_email
ATLASSIAN_TOKEN=your_token

You can set these:

  1. Directly in the Docker run command (recommended)
  2. Through a .env file (optional for local development, use the -env flag)
  3. Directly in your shell environment

Using with Claude and Cursor

To make Jira MCP work with Claude and Cursor, you need to add configuration to your Cursor settings.

Step 1: Install Jira MCP

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

Step 2: Configure Cursor

  1. Open Cursor
  2. Go to Settings > MCP > Add MCP Server
  3. Add the following configuration:
Option A: Using Docker (Recommended)
{
  "mcpServers": {
    "jira": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e", "ATLASSIAN_HOST=your_jira_instance.atlassian.net",
        "-e", "ATLASSIAN_EMAIL=your_email@example.com",
        "-e", "ATLASSIAN_TOKEN=your_atlassian_api_token",
        "ghcr.io/nguyenvanduocit/jira-mcp:latest"
      ]
    }
  }
}
Option B: Using Local Binary
{
  "mcpServers": {
    "jira": {
      "command": "/path/to/jira-mcp",
      "args": ["-env", "/path/to/.env"]
    }
  }
}

Step 3: Test Connection

You can test if the connection is working by asking Claude in Cursor:

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

Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.


For a list of recent changes, see CHANGELOG.md.

jira-mcp FAQ

How do I install jira-mcp?
You can install jira-mcp by downloading prebuilt binaries from the GitHub Releases page or building from source using Go 1.20+.
What Jira operations can jira-mcp perform?
jira-mcp supports issue creation, updates, searches, comments, worklogs, sprint management, issue linking, and workflow transitions.
Which AI assistants can integrate with jira-mcp?
jira-mcp is designed to work with AI assistants like Claude, and can be adapted for others such as OpenAI GPT-4 and Google Gemini.
What platforms does jira-mcp support?
jira-mcp provides binaries for Linux, macOS, and Windows platforms.
Is jira-mcp secure for enterprise use?
jira-mcp follows MCP principles for secure, scoped, and observable model interactions, suitable for enterprise environments.
Can jira-mcp handle complex Jira workflows?
Yes, jira-mcp supports transitioning issues through custom Jira workflows and managing sprint planning.
Does jira-mcp provide real-time Jira data access?
Yes, it enables AI models to retrieve and manipulate Jira data in real time for dynamic project management.