mcp-server-prometheus
@MCP-Mirror
About mcp-server-prometheus
Mirror of
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is mcp-server-prometheus?
mcp-server-prometheus is a TypeScript-based MCP server that bridges Claude with a Prometheus instance. It enables listing and reading Prometheus metric metadata and statistics through the Model Context Protocol.
How to use mcp-server-prometheus?
Configure the PROMETHEUS_URL environment variable (and optionally PROMETHEUS_USERNAME/PROMETHEUS_PASSWORD for basic auth). Add the server to your Claude Desktop config by pointing to the built index.js and setting the required environment. Use npm run build to compile, npm run watch for auto-rebuild, and npm run inspector for debugging.
Key features of mcp-server-prometheus
- List all available Prometheus metrics with descriptions
- Read detailed metric metadata and help text
- Access current statistical data (count, min, max)
- JSON mime type for structured metric access
- Basic authentication support for secured Prometheus instances
Use cases of mcp-server-prometheus
- Inspect Prometheus metric schema and metadata via Claude
- Retrieve current statistics for a specific metric
- Monitor Prometheus metric health without a dedicated dashboard
FAQ from mcp-server-prometheus
What environment variables are needed?
PROMETHEUS_URL is required. Optionally, set PROMETHEUS_USERNAME and PROMETHEUS_PASSWORD for basic authentication.
How do I add mcp-server-prometheus to Claude Desktop?
Add a JSON entry to the Claude Desktop config file (claude_desktop_config.json), specifying the command path to the built index.js and the required environment variables.
Can I debug the server?
Yes, use npm run inspector to launch the MCP Inspector, which provides a URL for browser-based debugging tools.
Does the server support authentication?
Yes, it supports basic authentication via PROMETHEUS_USERNAME and PROMETHEUS_PASSWORD environment variables.
What data does each metric resource return?
Each metric resource returns a JSON object containing the metric name, metadata (help text, type), and current statistics (count, min, max).
Frequently asked questions
What environment variables are needed?
`PROMETHEUS_URL` is required. Optionally, set `PROMETHEUS_USERNAME` and `PROMETHEUS_PASSWORD` for basic authentication.
How do I add mcp-server-prometheus to Claude Desktop?
Add a JSON entry to the Claude Desktop config file (`claude_desktop_config.json`), specifying the command path to the built `index.js` and the required environment variables.
Can I debug the server?
Yes, use `npm run inspector` to launch the MCP Inspector, which provides a URL for browser-based debugging tools.
Does the server support authentication?
Yes, it supports basic authentication via `PROMETHEUS_USERNAME` and `PROMETHEUS_PASSWORD` environment variables.
What data does each metric resource return?
Each metric resource returns a JSON object containing the metric name, metadata (help text, type), and current statistics (count, min, max).
Basic information
More Developer Tools MCP servers
Altronis
sypherinMCP server + CLI for Altronis — Singapore AI consulting. Ask the Lyra consultant, generate a grant-matched AI transformation plan, pull curated SG AI events/news. Read-only, wraps altronis.sg.
TalkToFigma
sonnylazuardiTalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
discoverGPT
Joe MonastierodiscoverGPT is visualAI's unified MCP gateway for AI commerce, exposing 29 tools across four capabilities on one canonical product catalog: trimodal search (natural-language, precise-color, and image-similarity), AI cata
AptiBuild AI — Career Intelligence
ParklandBuildsAptiBuild AI — Career Intelligence MCP Server Structured career decision scaffolding for AI agents. Provides personality-conditioned business idea generation, official BLS OEWS wage data, FRED labor market signals, and
endoflife.ai
endoflife.aiFree MCP server for software end-of-life intelligence: EOL dates, support status, and the 0-100 EOL Risk Score across 480+ tracked products. Agents can check a single version, pull a product's full lifecycle schedule, or
Comments