
MCP server for LLM-driven observability over Prometheus APIs.
Visit Prometheus MCP ServerThe Prometheus MCP Server is a Go-based Model Context Protocol (MCP) server designed to connect large language models (LLMs) with a running Prometheus instance through its API. It enables AI assistants to execute PromQL queries, analyze Prometheus metrics, review and modify configurations, search official documentation, and interact with alerting and recording rules, providing deep programmatic access and observability tooling to LLM-powered agents. Key features include support for TOON encoding to optimize LLM context/token efficiency, controllable data truncation, and the ability to enable TSDB Admin API tools for advanced data management. This makes it ideal for DevOps engineers, SREs, infrastructure teams, and tooling developers who want to build AI workflows or agents that monitor, manage, and reason about system health and metrics.
Visit Prometheus MCP Server's official website for product details and getting started.