Prometheus MCP Server

Fit and risk

Setup

{
  "mcpServers": {
    "prometheus": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PROMETHEUS_URL",
        "ghcr.io/pab1it0/prometheus-mcp-server:latest"
      ],
      "env": {
        "PROMETHEUS_URL": "<your-prometheus-url>"
      }
    }
  }
}

{
  "servers": {
    "prometheus": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PROMETHEUS_URL",
        "ghcr.io/pab1it0/prometheus-mcp-server:latest"
      ],
      "env": {
        "PROMETHEUS_URL": "<your-prometheus-url>"
      }
    }
  }
}

claude mcp add prometheus -e 'PROMETHEUS_URL=<your-prometheus-url>' -- docker run -i --rm -e PROMETHEUS_URL ghcr.io/pab1it0/prometheus-mcp-server:latest

Check that it works

After startup, tools like execute_query and list_metrics should appear in your MCP client's tool list; calling health_check or running a simple PromQL query (e.g., up) and getting a result confirms the connection works.

Troubleshooting

1. Verify PROMETHEUS_URL is correct and reachable from the environment.
2. Check authentication variables (username/password or token) are set correctly.
3. If SSL is enabled, ensure certificate paths or CA bundles are correct.
4. Inspect server logs for error messages and validate JSON configuration.

Things to try

Once connected, you can ask your AI assistant things like:

• List all available metrics in my Prometheus serverCopy
• Run a range query for CPU usage over the last hour with a 1-minute stepCopy
• Get the metadata for the http_requests_total metricCopy
• Show the current scrape targets and their statesCopy

Tools 6

No matching tools

Use cases

Supported clients

Listed from the project's documentation, not tested by this site.

Overview

Similar servers