prometheus-mcp-server and prometheus_mcp_server

Both tools are competing implementations of a Model Context Protocol (MCP) server designed to enable LLMs and AI agents to query and analyze Prometheus metrics.

prometheus-mcp-server
59
Established
prometheus_mcp_server
40
Emerging
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 23/25
Maintenance 0/25
Adoption 7/25
Maturity 16/25
Community 17/25
Stars: 379
Forks: 82
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 34
Forks: 11
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

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.

This project lets AI assistants like Claude Desktop or VS Code query and analyze Prometheus metrics. It takes your raw Prometheus data and allows an AI to execute PromQL queries, list metrics, and get metadata, providing insights directly within your AI development environment. It's designed for developers, DevOps engineers, or SREs who use AI tools for monitoring and troubleshooting.

observability site-reliability-engineering DevOps monitoring AI-assisted-troubleshooting

About prometheus_mcp_server

CaesarYangs/prometheus_mcp_server

A Model Context Protocol (MCP) server enabling LLMs to query, analyze, and interact with Prometheus databases through predefined routes.

This tool helps Site Reliability Engineers and DevOps professionals understand their system's health and performance by connecting Large Language Models (LLMs) to Prometheus databases. It allows LLMs to retrieve specific metrics, analyze data within custom time ranges, and explore usage patterns without needing to write complex PromQL queries manually. The output includes structured data and analyses from your Prometheus metrics.

Site Reliability Engineering DevOps System Monitoring Incident Response Performance Analysis

Scores updated daily from GitHub, PyPI, and npm data. How scores work