jira
Jira MCP.
claude mcp add --transport stdio xcollantes-jira-mcp uv --directory /ABSOLUTE/PATH/TO/REPO/ROOT run python -m src.main \ --env JIRA_API_TOKEN="your-api-token" \ --env JIRA_AUTH_TYPE="basic"
How to use
Jira MCP is a feature-rich MCP server that lets you control Jira directly from AI-powered clients using the Model Context Protocol. Once the server is running (via uv as shown in the installation section) you expose an MCP endpoint named jira that can be discovered and invoked by LLM clients like Claude Desktop, Cursor, Windsurf, or ChatGPT. The server relies on the jira-cli tool to issue Jira commands, so your Jira credentials are supplied through environment variables (JIRA_API_TOKEN and JIRA_AUTH_TYPE) and are passed to the Jira CLI during operation. Configure the mcpServers entry in your client’s configuration to point to the uv command that starts the server, and include the required environment variables so the client has access to Jira.
How to install
Prerequisites:
- Python 3.12 installed on your system
- UV installed (Installation instructions at https://docs.astral.sh/uv/getting-started/installation/)
- Access to a Jira instance (Cloud or Self-Hosted) and a Jira API token
Option A: Development setup using uv (recommended for local development)
- Clone the repository: git clone https://github.com/xcollantes/jira-mcp.git cd jira-mcp
- Install UV following the official instructions: <install UV per docs>
- Run the MCP server in development mode via uv (as described in the README example): uv --directory /ABSOLUTE/PATH/TO/REPO run python -m src.main
- Add the MCP server to your LLM client configuration using the command and environment variables shown in the mcp_config section above.
Option B: Run with binaries (not covered in this config but available in README)
- If you prefer binaries, download the latest release for your OS from the Jira MCP releases page and point your MCP client to the binary path similarly, supplying JIRA_API_TOKEN and JIRA_AUTH_TYPE in env.
Environment variables to set (example):
- JIRA_API_TOKEN: your-api-token
- JIRA_AUTH_TYPE: basic
Notes:
- Ensure jira-cli is installed and accessible from PATH if using the CLI inside the Python module.
- The Jira API token must be generated from your Jira account settings and granted the necessary permissions for the actions you will perform.
Additional notes
Tips and common issues:
- If UV cannot locate the repo path, ensure the --directory argument uses an absolute path to the jira-mcp repository root.
- When using macOS security, you may need to allow the uv process to access the repository directory in System Settings.
- Keep your JIRA_API_TOKEN secure; prefer passing env variables in your MCP client configuration rather than relying on shell environment variables.
- If you encounter Jira CLI authentication issues, verify JIRA_AUTH_TYPE matches the token mechanism (basic vs bearer) and that the token has not expired.
- For self-hosted Jira, ensure network access from the host running the MCP server to the Jira instance.
- The MCP server leverages jira-cli under the hood; install and configure jira-cli according to its official docs if you plan to test Jira CLI commands directly.
Related MCP Servers
PPTAgent
An Agentic Framework for Reflective PowerPoint Generation
mcp-aktools
📈 提供股票、加密货币的数据查询和分析功能MCP服务器
mcp -odoo
A Model Context Protocol (MCP) server that enables AI assistants to securely interact with Odoo ERP systems through standardized resources and tools for data retrieval and manipulation.
BinAssistMCP
Binary Ninja plugin to provide MCP functionality.
mcp -docy
A Model Context Protocol server that provides documentation access capabilities. This server enables LLMs to search and retrieve content from documentation websites by scraping them with crawl4ai. Built with FastMCP v2.
the -company
TheMCPCompany: Creating General-purpose Agents with Task-specific Tools