Provides tools for querying Prometheus metrics through instant and range queries, discovering metrics and metadata, retrieving series selectors and label values via the Prometheus HTTP API.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@prometheus-rsshow me the current status of all services with the query 'up'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Install
Cursor | VS Code |
On Linux, prefer
--network hostandhttp://localhost:9090in your config.Full instructions (prebuilt binaries, Cargo, Docker, Claude Desktop) in the docs: https://brenoepics.github.io/prometheus-mcp/installation
A minimal Model Context Protocol (MCP) server focused on reading from Prometheus. It exposes Prometheus discovery and query tools to MCP-compatible apps and includes a convenient CLI for local queries.
Highlights
Instant and range queries via Prometheus HTTP API
Discovery helpers: list metrics, get metadata, series selectors, label values
Optional internal metrics exporter at /metrics (disabled by default)
Works as a stdio MCP server or a one-off CLI
Container images
Images are published to both Docker Hub and GHCR:
Docker Hub:
brenoepics/prometheus-mcpGHCR:
ghcr.io/brenoepics/prometheus-mcp
Quickstart
Pick your preferred install method.
From crates.io (installs the
prometheus-mcpbinary):
Prebuilt binaries (GitHub Releases):
Download the latest release for your OS/arch: https://github.com/brenoepics/prometheus-mcp/releases
Docker (pull from Docker Hub or GHCR):
Installation
Build from source (Rust):
Or build a Docker image locally:
Usage (CLI)
The CLI mirrors the tools exposed over MCP.
Instant query
Range query
List metric names
Metric metadata
Series selectors (repeat --selector)
Label values
MCP server (stdio)
Start the MCP server over stdio:
Optional: enable internal metrics at /metrics (default off):
Running in Docker
Use the published image from Docker Hub (or GHCR alternative shown):
Linux alternatives when Prometheus runs on the host:
One-off CLI in the container:
Basic Auth
Pass credentials via environment variables or CLI flags.
Environment variables:
CLI flags:
Docker with env vars:
Configuration
All settings can be provided via environment variables; some also via flags.
Name | Type | Default | CLI flag | Description |
PROMETHEUS_URL | string (URL) | --prometheus-url | Base URL of your Prometheus server | |
PROMETHEUS_TIMEOUT | integer (seconds) | 10 | — | HTTP request timeout |
PROMETHEUS_RETRIES | integer | 3 | — | Number of retries for Prometheus API calls |
PROMETHEUS_RETRY_BACKOFF_MS | integer (ms) | 500 | — | Time to wait between retries |
PROMETHEUS_MIN_INTERVAL_MS | integer (ms) | — | — | Minimum interval between query requests (basic rate limit) |
PROMETHEUS_CACHE_TTL_SECS | integer (seconds) | — | — | TTL for simple in-process caches (list metrics and label values) |
PROMETHEUS_USERNAME | string | — | --prometheus-username | Basic auth username |
PROMETHEUS_PASSWORD | string | — | --prometheus-password | Basic auth password |
— | boolean | false | --mcp | Start MCP server over stdio |
— | boolean | false | --metrics-exporter | Enable internal Prometheus metrics at /metrics |
— | integer (port) | 9091 | --metrics-port | Port for /metrics when exporter is enabled |
See docs/configuration.md for notes and examples.
Accessing from Claude Desktop
Follow the official guide to locate claude_desktop_config.json:
https://modelcontextprotocol.io/quickstart/user#for-claude-desktop-users
Minimal Docker-based entry:
With host Prometheus and exporter (macOS/Windows):
With Basic Auth via environment variables:
More examples: see docs/claude-desktop.md.
Debugging
Use the MCP Inspector to exercise the server interactively:
Connect with transport "STDIO", command prometheus-mcp, and optional args --mcp --prometheus-url http://localhost:9090.
Logs are appended to /tmp/mcp.jsonl; tail it with:
Security Considerations
The server does not provide authentication itself; when running outside stdio, keep it on localhost.
Handle credentials via environment variables or your secret manager. Avoid committing secrets.
License
Apache-2.0