idanfishman/prometheus-mcp

A Model Context Protocol (MCP) server implementation that provides AI agents with programmatic access to Prometheus metrics via a unified interface.

56
/ 100
Established

This project integrates your AI assistant with Prometheus, allowing you to ask natural language questions about your monitoring data. You can input requests like "What's the CPU usage on server X?" and receive real-time metrics and insights directly from Prometheus. Site reliability engineers, DevOps professionals, and system administrators can use this to quickly understand system performance and health.

Available on npm.

Use this if you want to use an AI assistant (like GitHub Copilot, Claude Desktop, or Cursor) to easily query and analyze your Prometheus monitoring data using natural language.

Not ideal if you primarily interact with Prometheus through its native UI or direct API calls and do not use AI assistants for operational tasks.

site-reliability-engineering devops system-monitoring observability operations
Maintenance 10 / 25
Adoption 6 / 25
Maturity 24 / 25
Community 16 / 25

How are scores calculated?

Stars

24

Forks

6

Language

TypeScript

License

MIT

Last pushed

Feb 09, 2026

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/idanfishman/prometheus-mcp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.