mcp-jira-stdio
MCP server for Jira integration with stdio transport. Issue management, project tracking, and workflow automation via Model Context Protocol.
claude mcp add --transport stdio freema-mcp-jira-stdio npx mcp-jira-stdio@latest \ --env JIRA_EMAIL="Required: your Jira account email" \ --env JIRA_BASE_URL="Required: your Jira base URL (e.g., https://yourcompany.atlassian.net)" \ --env JIRA_API_TOKEN="Required: your Jira API token"
How to use
This MCP server integrates Jira's API with an MCP client, enabling reading, creating, updating, and querying Jira issues, projects, and related metadata directly from your MCP environment. Tools exposed include retrieving visible projects, fetching project info, getting and creating issues, searching with JQL, managing comments, and accessing Jira metadata, users, priorities, statuses, and custom fields. Once configured, you can call these tools from your MCP client to automate Jira workflows, track work, and manage issues without leaving your MCP context.
To use it, install and run the server as configured (via npx mcp-jira-stdio or your preferred setup), then invoke the tools by name through your MCP client. Ensure your environment variables for Jira authentication are set so tools can authenticate and perform actions. If credentials are missing or invalid, tool calls will fail with clear auth errors, but the server will still start and list available tools for discovery.
How to install
Prerequisites:
- Node.js v18 or higher
- npm or yarn
- Access to a Jira instance (Cloud or Server) and a Jira API token (or password for Server)
Install from npm (global):
npm install -g mcp-jira-stdio
Or install locally in a project:
npm install mcp-jira-stdio
Development setup (optional):
git clone https://github.com/freema/mcp-jira-stdio.git
cd mcp-jira-stdio
npm install
# Build if needed
npm run build
Configuration:
- Create a .env file or provide environment variables for JIRA_BASE_URL, JIRA_EMAIL, and JIRA_API_TOKEN as described in the README. Ensure these are accessible to the MCP process.
Running the server (example using npx as in the quick install):
npx mcp-jira-stdio@latest
If you prefer a local dev workflow, run the project directly after cloning and installing dependencies:
npm install
npm run dev
Additional notes
Notes and tips:
- Startup behavior: If Jira vars are missing, the server still starts and lists tools; tool calls will fail with a clear authentication error until you provide JIRA_BASE_URL, JIRA_EMAIL, and JIRA_API_TOKEN.
- Inspector: Use the MCP inspector for debugging and verifying tool inputs/outputs during development.
- Claude Desktop/Claude Code: You can configure via Claude Desktop JSON or Claude Code quick install commands (npx-based or direct command). Ensure env vars are injected into the MCP server configuration.
- Environment management: For security, avoid committing real credentials. Use environment-based configs or secret managers in production.
- Network requirements: Ensure the host running the MCP server can reach the Jira instance (firewall, VPN, or proxy settings may apply).
- Rate limits and permissions: Jira API endpoints may have rate limits or require specific permissions; configure scopes accordingly and implement retries as needed.
Related MCP Servers
sudocode
Lightweight agent orchestration dev tool that lives in your repo
systemprompt-code-orchestrator
MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.
airtable
Airtable integration for AI-powered applications via Anthropic's Model Context Protocol (MCP)
iron-manus
Iron Manus MCP
autonomo
Tired of 'it works' lies? Autonomo MCP makes your AI prove it—on real hardware, right in your editor.
pubnub
PubNub MCP Model Context Protocol Server for use in Cursor, Windsurf, Claude Desktop, Claude Code and OpenAI Codex and more!