rohitkhatana/jira_mcp_server

Jira MCP Server

A Model Context Protocol (MCP) server that provides Jira integration capabilities, allowing you to search and create Jira issues through MCP-compatible clients.

Features

• Search Issues: Query Jira issues using JQL (Jira Query Language)
• Create Issues: Create new Jira issues with project, summary, description, and issue type
• MCP Integration: Built on the Model Context Protocol for seamless integration with AI assistants

Prerequisites

• Python 3.11+
• uv package manager
• Jira instance with API access
• Jira API token

MCP Setup

To use this Jira MCP server with Claude Desktop, you need to configure it in your Claude Desktop configuration file.

For macOS Users

The configuration file is located at:

~/Library/Application Support/Claude/claude_desktop_config.json

Configuration Steps

1. Open your Claude Desktop configuration file in the path shown above
2. Add the Jira MCP server configuration to the mcpServers section:

{
    "mcpServers": {
        "jira": {
            "command": "/path/to/your/venv/bin/python",
            "args": ["/path/to/your/jira_mcp_server.py"],
            "env": {
                "JIRA_URL": "https://your-domain.atlassian.net",
                "JIRA_EMAIL": "your-email@example.com",
                "JIRA_API_TOKEN": "your-api-token"
            }
        }
    }
}

3. Replace the paths and credentials with your actual values:

   • command: Path to your Python virtual environment's python executable
   • args: Full path to the jira_mcp_server.py file
   • env: Your Jira credentials (same as in your .env file)

4. Restart Claude Desktop for the changes to take effect

Note: Make sure to use absolute paths for both the Python executable and the server script.

Setup

1. Install dependencies using uv:

   uv pip install -r requirements.txt
   

2. Set up environment variables: Create a .env file in the project root with your Jira credentials:

   JIRA_URL=https://your-domain.atlassian.net
   JIRA_EMAIL=your-email@example.com
   JIRA_API_TOKEN=your-api-token
   

3. Get your Jira API token:

   • Go to Atlassian Account Settings
   • Click "Create API token"
   • Give it a label and copy the token

Usage

Running the server

python jira_mcp_server.py

The server runs over stdio and is designed to be used with MCP-compatible clients.

Available Tools

Search Issues

• Name: search_issues
• Description: Search Jira issues using JQL
• Parameters:
  • jql (required): JQL query string

Create Issue

• Name: create_issue
• Description: Create a new Jira issue
• Parameters:
  • project (required): Project key
  • summary (required): Issue summary
  • description (optional): Issue description
  • issuetype (required): Issue type name

Example JQL Queries

• project = "PROJ" - All issues in a specific project
• assignee = currentUser() - Issues assigned to current user
• status = "Open" - Open issues
• created >= -7d - Issues created in the last 7 days

Development

This project uses:

• MCP: Model Context Protocol for AI assistant integration
• Jira Python: Official Jira REST API client
• AsyncIO: Asynchronous programming for better performance

License

[Add your license information here]

Contributing

[Add contribution guidelines here]