jira

This Jira MCP Server provides a robust, production-ready integration with Jira Cloud through a modular, TypeScript-based backend. It exposes a comprehensive set of tools for managing boards, issues, users, projects, time tracking, and comments, all with advanced features such as JQL search, rate limiting, and rich formatting in responses. You can interact with the server via the built-in MCP inspector to run individual tools or configure Claude Desktop to route natural language prompts to Jira operations. The server is designed for automation and AI agent workflows, delivering structured data and actionable responses for downstream apps and agents.

Prerequisites:

• Node.js 18 or higher
• npm (comes with Node.js)
• Jira Cloud account with API token

1. Install the MCP server globally (recommended for quick start):

npm install -g @orengrinker/jira-mcp-server
jira-mcp-server

2. Or run directly with npx (no installation):

npx @orengrinker/jira-mcp-server

3. Prepare environment variables (example):

export JIRA_BASE_URL=https://your-company.atlassian.net
export JIRA_EMAIL=your-email@company.com
export JIRA_API_TOKEN=your-jira-api-token
export LOG_LEVEL=INFO

4. Optional: configure Claude Desktop with the provided JSON snippet to load the Jira MCP server as a configured MCP source:

{
  "mcpServers": {
    "jira": {
      "command": "npx",
      "args": ["@orengrinker/jira-mcp-server"],
      "env": {
        "JIRA_BASE_URL": "https://your-company.atlassian.net",
        "JIRA_EMAIL": "your-email@company.com",
        "JIRA_API_TOKEN": "your-jira-api-token",
        "LOG_LEVEL": "INFO"
      }
    }
  }
}

5. If you prefer local development, clone the repo and run:

git clone https://github.com/OrenGrinker/jira-mcp-server.git
cd jira-mcp-server
npm install
npm run build
node dist/index.js

Tips and common considerations:

• Ensure your Jira API token has the required scopes (browse projects, edit/create issues, add comments, log work, etc.).
• The server includes rate limiting to respect Jira's API quotas; you can adjust behavior via environment variables if needed.
• Enable verbose logging (LOG_LEVEL=DEBUG) during troubleshooting to gain more insight into requests and responses.
• When using the inspector, you can test tools like get_boards, search_issues, create_issue, and add_worklog with JSON payloads.
• For production deployments, consider using a process manager (e.g., pm2) and securing environment variables via a vault or container orchestration secret management.
• If base URL or API token changes, restart the MCP server to apply new credentials.