About mcp-server-prometheus
mcp-server-prometheus is a TypeScript MCP server that gives clients such as Claude access to Prometheus metrics and data. It lists metrics and provides metadata and current statistics, with optional basic authentication.
Key features
- 01List Prometheus metrics and descriptions
- 02Read metric metadata and help text
- 03Provide count, min, and max statistics
- 04Support basic authentication
Use cases
- 01Let an MCP client inspect Prometheus metrics
- 02Check metric types, descriptions, and current statistics
MCP support
The server exposes Prometheus metrics as MCP resources, which clients can list and read as JSON data.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcp-server-prometheus
MCP server for interacting with Prometheus metrics and data.
This is a TypeScript-based MCP server that implements a Prometheus API interface. It provides a bridge between Claude and your Prometheus server through the Model Context Protocol (MCP).
Demo

Features
Resources
- List and access Prometheus metric schema
- Each metric resource provides:
- Metric name and description
- Detailed metadata from Prometheus
- Statistical information (count, min, max)
- JSON mime type for structured data access
Current Capabilities
- List all available Prometheus metrics with descriptions
- Read detailed metric information including:
- Metadata and help text
- Current statistical data (count, min, max values)
- Basic authentication support for secured Prometheus instances
Configuration
The server requires the following environment variable:
PROMETHEUS_URL: The base URL of your Prometheus instance
Optional authentication configuration:
PROMETHEUS_USERNAME: Username for basic auth (if required)PROMETHEUS_PASSWORD: Password for basic auth (if required)
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Installation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"mcp-server-prometheus": {
"command": "/path/to/mcp-server-prometheus/build/index.js",
"env": {
"PROMETHEUS_URL": "http://your-prometheus-instance:9090"
}
}
}
}
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
API Structure
The server exposes Prometheus metrics through the following URI structure:
- Base URI:
http://your-prometheus-instance:9090 - Metric URIs:
http://your-prometheus-instance:9090/metrics/{metric_name}
Each metric resource returns JSON data containing:
- Metric name
- Metadata (help text, type)
- Current statistics (count, min, max)
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.