MCP Catalogs
Home

prometheus-mcp-server

by pab1it0·442·Score 52

Prometheus MCP server enables AI agents to query and analyze metrics through standardized interfaces.

monitoringops-infradeveloper-tools
91
Forks
8
Open issues
this month
Last commit
2d ago
Indexed

Overview

This MCP server provides AI assistants with access to Prometheus metrics data through PromQL queries. It supports both instant and range queries, metric discovery, and metadata retrieval. The server offers multiple authentication methods including basic auth and bearer tokens, making it suitable for enterprise environments. It can be deployed via Docker, Kubernetes (Helm), or as a standalone application.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:AI-powered monitoring and alerting systems that can investigate anomalies
you:Automated infrastructure reporting by querying historical metrics trends
you:Developer assistants that help troubleshoot performance issues by querying relevant metrics
you:What authentication methods are supported?
you:Can I run multiple instances targeting different Prometheus servers?

When to choose this

Choose this server when you need AI agents to query Prometheus metrics and you prefer a containerized, production-ready solution with multiple deployment options.

When NOT to choose this

Don't choose this if you need write access to your metrics or are using a monitoring solution other than Prometheus.

Tools this server exposes

6 tools extracted from the README
  • health_check

    Health check endpoint for container monitoring and status verification

  • execute_query

    Execute a PromQL instant query against Prometheus

  • execute_range_query

    Execute a PromQL range query with start time, end time, and step interval

  • list_metrics

    List all available metrics in Prometheus with pagination and filtering support

  • get_metric_metadata

    Get metadata for one metric or bulk metadata with optional filtering

  • get_targets

    Get information about all scrape targets

Comparable tools

grafana-mcp-servermcp-datadogprometheus-client

Installation

Installation

Claude Desktop

Add to your Claude Desktop configuration:

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

Docker

docker run -i --rm \
  -e PROMETHEUS_URL="http://your-prometheus:9090" \
  ghcr.io/pab1it0/prometheus-mcp-server:latest

FAQ

What authentication methods are supported?
The server supports basic authentication with username/password, bearer token authentication, and mutual TLS authentication with client certificates.
Can I run multiple instances targeting different Prometheus servers?
Yes, you can use the TOOL_PREFIX configuration to run multiple instances with different prefixes, allowing you to target different environments.

Compare prometheus-mcp-server with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.