Prometheus MCP Server

What it does

Integrates Prometheus monitoring into your AI workflow. It enables LLMs to query time-series metrics, check service health, and analyze infrastructure signals using PromQL. This transforms your AI from a simple chatbot into a powerful observability assistant capable of diagnosing system issues through data.

Tools

• query_prometheus: Execute PromQL queries (Instant and Range) to fetch specific metric data.
• explore_metrics: List available metrics and their metadata to understand what is being tracked.
• check_health: Verify the connection status between the MCP server and the Prometheus instance.
• admin_status: Check active targets, alerts, and general server configuration.

Installation

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "prometheus-mcp": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "PROMETHEUS_URL=http://host.docker.internal:9090",
        "ghcr.io/polyglot-k/prometheus-mcp-server:latest"
      ]
    }
  }
}

Supported hosts

• Claude Desktop