MCP Servers

Prometheus MCP Server (Community)

Last updated September 23, 2025

Open-source MCP server to query and analyze Prometheus metrics (PromQL, metadata, alerts).

The Prometheus MCP Server is an open-source server implementation that exposes Prometheus-hosted time-series metrics, metadata, scrape target info, alerts/rules, and more through the Model Context Protocol. This allows AI assistants or tools like Claude, Cursor, and Windsurf to access metrics (instant/range queries, metadata) and perform observability and diagnostics tasks via standard MCP RPC tools.

Key features

  • PromQL instant queries and range queries via MCP
  • Metric discovery and metadata retrieval
  • Scrape target/server status and alerting/rule insights (per implementation)
  • Configurable transports (stdio, HTTP) and env-based auth/URLs
  • Docker-friendly deployment and community OSS

Related tools

  • SigNoz MCP Server

    An MCP server that connects AI assistants with SigNoz observability data for metrics, alerts, dashboards, and service monitoring.

  • Grafana MCP Server

    MCP server for Grafana integration, enabling AI assistants to access dashboards, metrics, and observability data.

  • Axiom MCP Server

    An MCP server that connects AI assistants with Axiom datasets via Axiom Processing Language (APL).

  • Sentry MCP Server

    MCP server for Sentry integration, enabling AI assistants to access error tracking, issue management, and debugging workflows.

  • GCP MCP Server

    Official MCP servers that connect AI assistants with Google Cloud services via the gcloud CLI and Observability APIs.