prometheus-mcp-server and prometheus-mcp
Both projects appear to be competing implementations of a Model Context Protocol (MCP) server designed to expose Prometheus metrics to AI agents and LLMs.
About prometheus-mcp-server
pab1it0/prometheus-mcp-server
A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
Exposes PromQL query execution (instant and range queries) and metric discovery tools through MCP's standardized interface, supporting multiple authentication methods (basic auth, bearer tokens, mTLS) and transport modes (stdio, HTTP, SSE). Built in Python with Docker and Kubernetes deployment options, integrating seamlessly with MCP-compatible clients like Claude Desktop, VS Code, Cursor, and Windsurf for agentic metric analysis workflows.
About prometheus-mcp
idanfishman/prometheus-mcp
A Model Context Protocol (MCP) server implementation that provides AI agents with programmatic access to Prometheus metrics via a unified interface.
Supports both stdio and HTTP transports with configurable tool categories (discovery, info, query) that can be selectively enabled based on security requirements. Integrates directly with Prometheus APIs using structured JSON responses optimized for LLM consumption, and deploys across VS Code, Cursor, Windsurf, Claude Desktop, and Docker environments.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work