Skip to main content
Glama
Sign In

Jira MCP Server

by brukhabtu
GitHub
Python
OverviewInspectNewSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

Jira MCP Server

A production-ready Jira MCP server using FastMCP 2.0's OpenAPI integration. Automatically exposes your entire Jira instance through the Model Context Protocol (MCP) with zero configuration overhead.

Features

  • 🚀 Zero-maintenance OpenAPI integration - Automatically generates MCP tools from Jira's official API specification
  • 🔐 Secure authentication - Uses Jira API tokens with environment variable support
  • 🌐 Multiple transports - Support for stdio, HTTP, and SSE protocols
  • ⚡ Fast and lightweight - Minimal overhead with async HTTP client
  • 🔧 Production-ready - Type-safe, well-tested, and follows security best practices
  • 📝 Self-documenting - All Jira API endpoints automatically become available as MCP tools

Quick Start

1. Installation

# Clone and install git clone <repository-url> cd jira_mcp uv sync

2. Setup Jira API Token

  1. Go to Atlassian Account Settings
  2. Create an API token
  3. Note your Jira instance URL (e.g., https://yourcompany.atlassian.net)

3. Set Environment Variables

export JIRA_BASE_URL="https://yourcompany.atlassian.net" export JIRA_API_USER="your-email@company.com" export JIRA_API_TOKEN="your-api-token"

4. Run the Server

# Default configuration (stdio transport) jira-mcp # Or with custom transport jira-mcp --transport http --port 8080

How It Works

The server automatically:

  1. Downloads Jira's official OpenAPI specification
  2. Generates MCP tools for every Jira API endpoint
  3. Authenticates requests using your API token
  4. Exposes your entire Jira instance through MCP

This means you get instant access to:

  • Issue management (create, update, search, transition)
  • Project administration
  • User and permission management
  • Dashboards and filters
  • Webhooks and automation
  • And every other Jira Cloud API feature!

Configuration

Environment Variables

VariableRequiredDefaultDescription
JIRA_BASE_URL✅-Your Jira instance URL (e.g., https://company.atlassian.net)
JIRA_API_USER✅-Your Jira username/email address
JIRA_API_TOKEN✅-Your Jira API token
JIRA_TIMEOUT❌30HTTP timeout in seconds
MCP_TRANSPORT❌stdioTransport method (stdio, http, sse)
MCP_PORT❌8000Port for HTTP/SSE transports
MCP_LOG_LEVEL❌INFOLogging level (DEBUG, INFO, WARNING, ERROR)

Command Line Options

jira-mcp [OPTIONS] Options: --transport {stdio,http,sse} Transport method (overrides MCP_TRANSPORT env var) --port PORT Port for HTTP/SSE transport (overrides MCP_PORT env var) --version Show version and exit --help Show help message

Integration with MCP Clients

Option 1: Using pre-built Docker image (easiest)

{ "mcpServers": { "jira": { "command": "docker", "args": [ "run", "--rm", "-i", "--env", "JIRA_BASE_URL=https://yourcompany.atlassian.net", "--env", "JIRA_API_USER=your-email@company.com", "--env", "JIRA_API_TOKEN=your-api-token", "ghcr.io/brukhabtu/jira-mcp:latest" ] } } }

Option 2: Using environment variables (more secure)

Set your credentials in your shell profile (.bashrc, .zshrc, etc.):

export JIRA_BASE_URL="https://yourcompany.atlassian.net" export JIRA_API_USER="your-email@company.com" export JIRA_API_TOKEN="your-api-token"

Then use this config:

{ "mcpServers": { "jira": { "command": "docker", "args": [ "run", "--rm", "-i", "--env", "JIRA_BASE_URL", "--env", "JIRA_API_USER", "--env", "JIRA_API_TOKEN", "ghcr.io/brukhabtu/jira-mcp:latest" ] } } }

Option 3: Local installation (if you prefer)

# Install with uv git clone https://github.com/brukhabtu/jira-mcp.git cd jira-mcp uv sync uv pip install -e .
{ "mcpServers": { "jira": { "command": "jira-mcp", "env": { "JIRA_BASE_URL": "https://yourcompany.atlassian.net", "JIRA_API_USER": "your-email@company.com", "JIRA_API_TOKEN": "your-api-token" } } } }

Advanced Docker Usage

Running as HTTP Service (for multiple clients)

# Run as background service docker run -d --name jira-mcp \ -p 8000:8000 \ -e JIRA_BASE_URL=https://yourcompany.atlassian.net \ -e JIRA_API_USER=your-email@company.com \ -e JIRA_API_TOKEN=your-api-token \ -e MCP_TRANSPORT=http \ --restart unless-stopped \ ghcr.io/brukhabtu/jira-mcp:latest # Connect via HTTP from any MCP client # Server will be available at http://localhost:8000

Other MCP Clients

The Docker image supports all MCP transport protocols:

  • stdio: For local desktop applications (Claude Desktop, etc.)
  • HTTP: For web applications and remote clients
  • SSE: For real-time web applications

Example HTTP usage:

# Start HTTP server docker run -p 8000:8000 \ -e MCP_TRANSPORT=http \ -e JIRA_BASE_URL=https://yourcompany.atlassian.net \ -e JIRA_API_USER=your-email@company.com \ -e JIRA_API_TOKEN=your-api-token \ ghcr.io/brukhabtu/jira-mcp:latest # Connect from any HTTP MCP client to http://localhost:8000

Docker

Build and run with Docker:

# Build the image docker build -t jira-mcp . # Run with stdio transport (default) docker run -e JIRA_BASE_URL=https://your-domain.atlassian.net \ -e JIRA_API_USER=your-email@example.com \ -e JIRA_API_TOKEN=your-api-token \ jira-mcp # Run with HTTP transport docker run -p 8000:8000 \ -e JIRA_BASE_URL=https://your-domain.atlassian.net \ -e JIRA_API_USER=your-email@example.com \ -e JIRA_API_TOKEN=your-api-token \ -e MCP_TRANSPORT=http \ jira-mcp # Use pre-built image from GitHub Container Registry docker run ghcr.io/brukhabtu/jira-mcp:latest

Development

Setup

# Install dependencies uv sync # Run all tests (55 unit and integration tests) uv run pytest # Run only unit tests uv run pytest tests/unit/ # Run only integration tests uv run pytest tests/integration/ # Type checking (mypy strict mode) uv run mypy jira_mcp/ # Code formatting and linting uv run ruff check . uv run ruff format .

Architecture

  • jira_mcp/config.py: Pydantic models with environment variable loading
  • jira_mcp/auth.py: HTTP client with Jira Basic Auth
  • jira_mcp/server.py: FastMCP integration with OpenAPI spec fetching
  • jira_mcp/__main__.py: CLI interface with environment-based configuration

Testing

The project includes 41 unit tests organized in tests/unit/ covering:

  • Configuration validation and edge cases
  • Authentication and HTTP client behavior
  • Server initialization and error handling
  • Environment variable parsing and type conversion

Troubleshooting

Common Issues

"Configuration error" on startup: Check that all required environment variables (JIRA_BASE_URL, JIRA_API_USER, JIRA_API_TOKEN) are set.

Authentication errors: Verify your API token is correct and your email matches your Jira account.

Connection timeout: Check your JIRA_BASE_URL is correct and accessible. Increase JIRA_TIMEOUT if needed.

Claude Desktop not finding server: Ensure environment variables are available to GUI applications (may require restart or launchctl setenv on macOS).

Getting Help

  • Check the CLAUDE.md file for development guidance
  • Review test files for usage examples
  • Run jira-mcp --help for command line options

Security

  • API tokens are stored in environment variables, never in code or config files
  • All HTTP requests use TLS encryption
  • No sensitive data is logged or exposed
  • Follows OAuth 2.0 and Atlassian security best practices

License

MIT

This server cannot be installed

-
security - not tested
F
license - not found
-
quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A production-ready server that automatically exposes your entire Jira instance through the Model Context Protocol, allowing seamless interaction with Jira's API features including issue management, project administration, and user management.

  1. Features
    1. Quick Start
      1. Installation
      2. Setup Jira API Token
      3. Set Environment Variables
      4. Run the Server
    2. How It Works
      1. Configuration
        1. Environment Variables
        2. Command Line Options
      2. Integration with MCP Clients
        1. Claude Desktop (Docker - Recommended)
        2. Advanced Docker Usage
        3. Other MCP Clients
      3. Docker
        1. Development
          1. Setup
          2. Architecture
          3. Testing
        2. Troubleshooting
          1. Common Issues
          2. Getting Help
        3. Security
          1. License

            Related MCP Servers

            • Python Jira MCP Server

              Chase-Bullock
              -
              security
              F
              license
              -
              quality
              A server implementation that allows AI models to interact with Jira through the Model Context Protocol, enabling tasks like JQL searches and retrieving issue details.
              Last updated -
              Python

            • Jira MCP Server

              ParasSolanki
              A
              security
              A
              license
              A
              quality
              A Model Context Protocol server that provides integration with Jira, allowing Large Language Models to interact with Jira projects, boards, sprints, and issues through natural language.
              Last updated -
              5
              87
              2
              TypeScript
              MIT License
              • Apple

            • Jira MCP Server

              InfinitIQ-Tech
              -
              security
              A
              license
              -
              quality
              A Model Context Protocol server that enables interaction with Jira's REST API using natural language commands, allowing users to manage Jira projects, issues, comments, and workflows through Claude Desktop and other MCP clients.
              Last updated -
              1
              Python
              MIT License

            • Jira MCP Server

              maximepeabody
              -
              security
              A
              license
              -
              quality
              A Simple Model Context Protocol server that enables AI assistants to interact with Jira, allowing operations like fetching tickets, adding comments, and updating ticket status.
              Last updated -
              1
              Python
              Apache 2.0

            View all related MCP servers

            New MCP Servers

            MCP directory API

            We provide all the information about MCP servers via our MCP API.

            curl -X GET 'https://glama.ai/api/mcp/v1/servers/brukhabtu/jira-mcp'

            If you have feedback or need assistance with the MCP directory API, please join our Discord server