The Prometheus MCP Server provides access to Prometheus metrics and queries through standardized Model Context Protocol (MCP) interfaces, enabling AI assistants to execute PromQL queries and analyze metrics data.
From the registry: MCP server providing Prometheus metrics access and PromQL query execution for AI assistants
Please install the `prometheus-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Prometheus server** — A running Prometheus instance accessible from your environment
Canonical MCP server config (stdio transport):
- command: `docker`
- args: ["run","-i","--rm","-e","PROMETHEUS_URL","ghcr.io/pab1it0/prometheus-mcp-server:latest"]
- required environment variables:
- `PROMETHEUS_URL`: URL of the Prometheus server (example: `http://your-prometheus:9090`)
- optional environment variables:
- `PROMETHEUS_USERNAME`: Username for basic authentication (example: `<username>`)
- `PROMETHEUS_PASSWORD`: Password for basic authentication (example: `<password>`)
- `PROMETHEUS_TOKEN`: Bearer token for authentication (example: `<token>`)
- `PROMETHEUS_URL_SSL_VERIFY`: Set to False to disable SSL verification (example: `False`)
- `PROMETHEUS_MCP_SERVER_TRANSPORT`: Transport mode: stdio, http, sse (example: `stdio`)
- `ORG_ID`: Organization ID for multi-tenant setups (example: `<org-id>`)
Note: Docker is the canonical install. Also supports uvx/pip install. Helm chart available for Kubernetes. PROMETHEUS_URL is required.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.PROMETHEUS_URLrequiredURL of your Prometheus serverReal-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.