mcp-jira
MCP Server for handling Jira issues
Documentation
Jira MCP Server
A Model Context Protocol (MCP) server for interacting with Jira's REST API using the `jira-python` library. This server integrates with Claude Desktop and other MCP clients, allowing you to interact with Jira using natural language commands.
Features
- Get all accessible Jira projects
- Get details for a specific Jira issue
- Search issues using JQL (Jira Query Language)
- Create new Jira issues
- Add comments to issues
- Get available transitions for an issue
- Transition issues to new statuses
Installation
Prerequisites
- Python 3.9 or higher
- A Jira instance (Cloud, Server, or Data Center)
- uv (optional but recommended for dependency management)
Activate a virtual environment (recommended)
# Install a Virtual Environment (VENV) in the mcp server directory
python -m venv .
# Activate the virtual environment
source bin/activateUsing uv (recommended)
# Install uv if you don't have it
pip install uv
# Install the Jira MCP server
uv pip install mcp-server-jiraUsing pip
pip install mcp-server-jiraConfiguration
Environment Variables
Configure the server using environment variables:
- `JIRA_SERVER_URL`: URL of your Jira server
- `JIRA_AUTH_METHOD`: Authentication method ('basic_auth' or 'token_auth')
- `JIRA_USERNAME`: Username for basic auth
- `JIRA_PASSWORD`: Password for basic auth
- `JIRA_TOKEN`: API token or Personal Access Token
Environment File (Local Development)
You can also create a `.env` file in the root directory with your configuration:
JIRA_SERVER_URL=https://your-jira-instance.atlassian.net
JIRA_AUTH_METHOD=basic_auth
JIRA_USERNAME=your_email@example.com
JIRA_TOKEN=your_api_tokenUsage
Command Line
python -m mcp_server_jiraDocker
docker build -t mcp-jira .
docker run --env-file .env -p 8080:8080 mcp-jiraClaude Desktop Integration
To use this server with Claude Desktop:
1. Install the server using one of the methods above
2. In Claude Desktop:
(`NOTE`: The environment variables used are for token Auth and will not work with other authentication methods)
{
"mcpServers": {
"jira": {
"command": " i.e. /Users//.local/bin/uv",
"args": [
"--directory",
"",
"run",
"mcp-server-jira"
],
"env": {
"JIRA_SERVER_URL": "https://.atlassian.net/",
"JIRA_AUTH_METHOD": "token_auth",
"JIRA_USERNAME": "",
"JIRA_TOKEN": ""
}
}
}
}3. Now you can interact with Jira by asking Claude questions like:
Authentication
The server supports multiple authentication methods:
Basic Authentication
For Jira Server/Data Center with username and password:
JIRA_SERVER_URL="https://jira.example.com"
JIRA_AUTH_METHOD="basic_auth"
JIRA_USERNAME="your_username"
JIRA_PASSWORD="your_password"API Token (Jira Cloud)
For Jira Cloud using an API token:
JIRA_SERVER_URL="https://your-domain.atlassian.net"
JIRA_AUTH_METHOD="basic_auth"
JIRA_USERNAME="your_email@example.com"
JIRA_TOKEN="your_api_token"Personal Access Token (Jira Server/Data Center)
For Jira Server/Data Center (8.14+) using a PAT:
JIRA_SERVER_URL="https://jira.example.com"
JIRA_AUTH_METHOD="token_auth"
JIRA_TOKEN="your_personal_access_token"Available Tools
1. `get_projects`: Get all accessible Jira projects
2. `get_issue`: Get details for a specific Jira issue by key
3. `search_issues`: Search for Jira issues using JQL
4. `create_issue`: Create a new Jira issue
5. `add_comment`: Add a comment to a Jira issue
6. `get_transitions`: Get available workflow transitions for a Jira issue
7. `transition_issue`: Transition a Jira issue to a new status
License
MIT
Frequently asked questions
What is mcp-jira?
mcp-jira is MCP Server for handling Jira issues
How do I install mcp-jira?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-jira open source?
Yes — it is hosted on GitHub at https://github.com/InfinitIQ-Tech/mcp-jira and has 7 stars.
Related MCP tools
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Automate browser based workflows with AI
Hindsight: Agent Memory That Learns
A privacy-first app that strips AI watermarks from content you own.
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP