Prometheus

Provides access to Prometheus data via MCP with HTTP and CLI run options.

python

1

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

This MCP server exposes Prometheus data through a Model Context Protocol (MCP) interface, allowing MCP clients to query Prometheus metrics and series efficiently. It provides easy ways to run locally or integrate into client workflows so you can build powerful data-driven experiences.

How to use

You connect to the Prometheus MCP server from your MCP client by pointing it at a Prometheus-enabled endpoint and using the MCP data access capabilities the server exposes. You can either run the server locally via a CLI command or run it directly from your environment without a formal installation. In both cases, provide your Prometheus server URL to enable data access and evaluation.

How to install

Prerequisites vary by installation method. You need a Node.js environment to use the Smithery option, or a Python-enabled environment to use the direct Python installation.

Additional sections

Install options and runtime commands shown here let you run the MCP server against your Prometheus instance. If you plan long-term usage, consider installing the package to access a stable, reusable command across sessions.