Enables access to Prometheus monitoring and time-series data through an MCP server, allowing AI assistants to query metrics, analyze performance data, and interact with Prometheus instances.
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 MCP Servershow me the CPU usage for the last hour"
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.
Prometheus MCP Server
A tool that allows access to Prometheus data through a Model Context Protocol server.
Installation
pipx install git+https://github.com/moohoorama/prometheus-mcp-server-py.gitRun Without Installation
You can also run the package directly without installing it using pipx run:
pipx run --spec git+https://github.com/moohoorama/prometheus-mcp-server-py.git prometheus-mcp --url http://your-prometheus-server:9090This is useful for testing or one-time usage scenarios.
Related MCP server: Prometheus MCP Server
Usage
# Command line arguments
prometheus-mcp --url http://your-prometheus-server:9090 \
--username username \
--password password
# Or
prometheus-mcp --url http://your-prometheus-server:9090 \
--token your-tokenCommand Line Arguments
--url: Prometheus server URL (required)--username: Username for basic authentication (optional)--password: Password for basic authentication (optional)--token: Token for authentication (optional)--org-id: Organization ID for multi-tenant setups (optional)