Prometheus MCP Server

🚀 Prometheus MCP Server

A Model Context Protocol (MCP) server for Prometheus. This implementation provides access to your Prometheus metrics and queries through a standardized MCP interface, allowing AI assistants to execute PromQL queries and analyze your metric data.

✨ Features

• [x] Execute PromQL queries to Prometheus
• [x] Discover and explore metrics
  • [x] List available metrics
  • [x] Get metadata for specific metrics
  • [x] View instant query results
  • [x] View range query results with different step intervals
• [x] Support authentication
  • [x] Use basic authentication from environment variables
  • [x] Use bearer token authentication from environment variables
• [x] Support Docker containerization
• [x] Provide interactive tools for AI assistants

The list of tools is configurable, so you can choose which tools to provide to MCP clients. This is useful when you don't use certain features or don't want to occupy too much of the context window.

🚀 Quick Start

💡 Prerequisites

1. Ensure that your Prometheus server is accessible from the environment where this MCP server is running.

⚙️ Configuration

2. Configure environment variables to obtain Prometheus server information, either through a .env file or system environment variables:

# Required: Prometheus configuration
PROMETHEUS_URL=http://your-prometheus-server:9090

# Optional: Authentication credentials (if required)
# Choose one of the following authentication methods as needed:

# For basic authentication
BASIC_AUTH_USERNAME=your_username
BASIC_AUTH_PASSWORD=your_password

# For bearer token authentication
BEARER_TOKEN=your_bearer_token

# Other optional configurations
ScrapeInterval=60  # Interval in seconds
ScrapeTimeout=10    # Scrape timeout in seconds

🚀 Installation and Running

3. Install and run the server:

uv install
uv run

📚 Documentation

📁 Project Structure

The project has organized an src directory structure:

prometheus-mcp-server/
├── src/
│   └── prometheus_mcp_server/
│       ├── __init__.py      # Package initialization file
│       ├── server.py        # MCP server implementation
│       └── main.py          # Main application logic
├── Dockerfile               # Docker configuration file
├── docker-compose.yml       # Docker Compose configuration file
├── .dockerignore            # Docker ignore file
└── README.md                # This file

🧪 Testing

The project includes a comprehensive test suite to ensure functionality and prevent regressions.

Run tests:

# Install development dependencies
uv pip install -e ".[dev]"

# Run tests
pytest

# Generate a coverage report
pytest --cov=src --cov-report=term-missing

💻 Usage Examples

🛠️ Tools

📄 License

This project is licensed under the MIT License.