Vibe Coding Discoverprometheus-mcp-server
View on GitHubA Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
MCP server exposing Prometheus to AI agents: run PromQL instant and range queries, list metrics, read metric metadata and inspect scrape targets. Ships as Docker image and Helm chart with stdio/HTTP/SSE transports, auth, and multi-tenant support.
Use Cases
Let AI assistants run PromQL instant queriesRun PromQL range queries over time windowsDiscover and list available Prometheus metricsFetch metric metadata and search by name/descriptionInspect scrape targets and their health stateDebug incidents by asking an LLM about live metricsAttach Prometheus context to Claude Desktop, Cursor, VS Code or WindsurfDeploy a metrics MCP server to Kubernetes via HelmMulti-tenant Prometheus querying via ORG_IDAuthenticated Prometheus access with basic auth, bearer token or mTLS
Built With
- Language
- Python
- Frameworks
- FastMCP · Starlette · Docker · Kubernetes · Helm · pytest · uv · python-dotenv · structlog
Tags
mcp · mcp-server · prometheus · promql · observability · monitoring · metrics · devops · llm · ai-agents · python · docker · kubernetes · helm · sre · claude-desktop