Prometheus MCP Server is a Model Context Protocol server that provides seamless integration with Prometheus. It enables AI assistants to query metrics, discover available data, and analyze system performance through natural language interactions. The server offers real-time access to current and historical metrics, and supports metrics discovery to list available metrics and monitoring targets. It includes a full type-safe TypeScript implementation and supports multiple authentication methods (Basic auth, Bearer tokens, and TLS) for secure access. Deployment is flexible via npx (recommended) or a global installation, with configuration driven by environment variables such as PROMETHEUS_URL and optional credentials, timeouts, and insecure connections. A built-in set of Tools (prom_query, prom_range, prom_discover, prom_metadata, prom_targets) exposes common Prometheus operations for AI-driven queries, graphing, discovery, metric metadata, and target health. This MCP server is designed for AI-driven workflows, enabling natural language interaction with Prometheus data while ensuring secure, scalable access.