jira

This Jira MCP Server exposes a comprehensive set of Model Context Protocol tools that let Claude-enabled assistants interact with Jira directly. You can retrieve project information, list issues, create and update issues and subtasks, manage workflows and transitions, and perform bulk operations across multiple issues. The server also supports granular label and component management, issue linking, comments, and user management tasks. Use the provided operation examples to craft prompts for your AI assistant, and the server will translate those into Jira REST API calls with validation and structured responses.

Prerequisites:

• Node.js 18 or higher
• Access to a Jira Cloud or Server instance
• Jira API token (Cloud) or username/password (Server)
• Claude Desktop or another MCP-compatible AI assistant

1. Clone the repository:

   git clone https://github.com/yourusername/jira-server.git
   cd jira-server
   

2. Install dependencies:

   npm install
   

3. Set up environment variables:

   cp .env.example .env
   

4. Edit the .env file with your Jira credentials:

   JIRA_HOST=your-instance.atlassian.net
   JIRA_EMAIL=your-email@example.com
   JIRA_API_TOKEN=your-api-token
   

5. Build the server (if required by the project):

   npm run build
   

6. Start the server:

   npm start
   

Optional during development:

• Development mode with auto-reload:

  npm run dev
  

• Linting and formatting:

  npm run lint
  npm run format
  

Environment variables control Jira credentials and logging. Common issues include invalid Jira host or API token, network restrictions, or insufficient permissions on the Jira account. If you add custom fields, ensure the field names match your Jira instance. Use LOG_LEVEL to reduce or increase verbosity during debugging. When configuring Claude Desktop, provide the absolute path to the Jira server project and populate the environment variables in Claude's config. For bulk operations, verify the impact on large sets of issues to avoid unintended changes.