MCP

Query Prometheus Metrics with AI

Name: Query Prometheus Metrics with AI
Availability: OnlineOnly
Author: Pavel Shklovsky

Connect AI to Prometheus metrics and PromQL queries for monitoring data analysis. Execute queries and explore metrics.

Connect

Works with prometheus

Pavel Shklovsky

Maintainer?

Spark score

out of 100

Updated 4 months ago

Version 1.0.0

Models

claude

Add to Favorites

Why it matters

Enable AI assistants to directly query and analyze your Prometheus monitoring data. Execute PromQL queries, explore metrics, and gain insights into system health and performance.

Outcomes

What it gets done

Execute instant and range PromQL queries.

List and retrieve metadata for Prometheus metrics.

Access data collection target information.

Authenticate with Prometheus using basic auth or bearer tokens.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-prometheus | bash

Capabilities

Tools your agent gets

health_check

Health check for container monitoring and status verification

execute_query

Execute an instant PromQL query against Prometheus

execute_range_query

Execute a range PromQL 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 a specific metric

get_targets

Get information about all data collection targets

Overview

Prometheus MCP Server

What it does

This MCP server provides AI assistants with access to Prometheus metrics and the ability to execute PromQL queries. It allows for metric discovery, exploration, and retrieval of both instant and range query results. The connector supports authentication and is containerized with Docker for easy deployment.

How it connects

Use this connector when you need to integrate AI assistants with your Prometheus monitoring infrastructure. It is ideal for automating analysis of system performance, troubleshooting, and gaining insights from time-series data.

Source README

An MCP server that provides access to Prometheus metrics and queries, enabling AI assistants to execute PromQL queries and analyze monitoring data.

Installation

Docker

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

Docker with Authentication

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

From Source

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv
source .venv/bin/activate
uv pip install -e .

Configuration

Claude Desktop

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

VS Code / Cursor / Windsurf

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

Available Tools

Tool	Description
`health_check`	Health check for container monitoring and status verification
`execute_query`	Execute an instant PromQL query against Prometheus
`execute_range_query`	Execute a range PromQL 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 a specific metric
`get_targets`	Get information about all data collection targets

Features

Execution of PromQL queries against Prometheus
Metric discovery and exploration
Viewing available metrics
Getting metadata for specific metrics
Viewing instant query results
Viewing range query results with various step intervals
Authentication support (Basic auth and Bearer token)
Docker containerization support
Interactive tools for AI assistants
Customizable tool list

Environment Variables

Required

PROMETHEUS_URL - URL of your Prometheus server

Optional

PROMETHEUS_URL_SSL_VERIFY - Set to False to disable SSL verification
PROMETHEUS_DISABLE_LINKS - Set to True to disable links to Prometheus UI in query results (saves context tokens)
PROMETHEUS_USERNAME - Username for basic authentication
PROMETHEUS_PASSWORD - Password for basic authentication
PROMETHEUS_TOKEN - Bearer token for authentication
ORG_ID - Organization ID for multi-tenant setups
PROMETHEUS_MCP_SERVER_TRANSPORT - Transport mode (stdio, http, sse)
PROMETHEUS_MCP_BIND_HOST - Host for HTTP transport

Notes

Requires a Prometheus server accessible from your environment and an MCP-compatible client. Available through Docker Desktop MCP Catalog for easy installation.

Discussion