Prometheus MCP Server
A Model Context Protocol (MCP) server for Prometheus. This server enables AI assistants to query and analyze Prometheus metrics through standardized MCP interfaces, facilitating PromQL query execution and data analysis.
Key Features:
- PromQL Execution: Executes PromQL queries against Prometheus.
- Metric Discovery:
- Lists available metrics.
- Retrieves metadata for specific metrics.
- Provides instant and range query results.
- Authentication Support:
- Basic and Bearer token authentication.
- Containerization: Docker support for easy deployment.
- Interactive Tools: Configurable tools for AI assistants.
Usage:
- Ensure Prometheus is accessible.
- Configure environment variables (Prometheus URL, username, password, or token).
- Add server configuration to the client (e.g., Claude Desktop).
Docker Usage:
Build the Docker image:
docker build -t prometheus-mcp-server .Run with Docker Compose or directly, configuring environment variables.
Development:
Contributions are welcome. The project uses uv for dependency management. Tests are organized into configuration validation, server functionality, error handling, and main application tests.
