A Model Context Protocol (MCP) server implementation that provides AI agents with programmatic access to Prometheus metrics via a unified interface.
Overview
A Model Context Protocol (MCP) server that provides seamless integration between AI assistants and Prometheus, enabling natural language interactions with your monitoring infrastructure. This server allows for effortless querying, discovery, and analysis of metrics through Visual Studio Code, Cursor, Windsurf, Claude Desktop, and other MCP clients. - . Direct API integration with Prometheus, no complex parsing needed. - . Structured JSON responses optimized for AI assistant consumption. - . Enable/disable tool categories based on your security and operational requirements. - . Works with both stdio and HTTP transports for maximum compatibility. - Node.js 20.19.0 or newer - Access to a Prometheus server - VS Code, Cursor, Windsurf, Claude Desktop or any other MCP client First, install the Prometheus MCP server with your client. A typical configuration looks like this: After installation, the Prometheus MCP server will be available for use with your GitHub Copilot agent in VS Code.
README
Prometheus MCP Server
Key Features
- Fast and lightweight. Direct API integration with Prometheus, no complex parsing needed.
- LLM-friendly. Structured JSON responses optimized for AI assistant consumption.
- Configurable capabilities. Enable/disable tool categories based on your security and operational requirements.
- Dual transport support. Works with both stdio and HTTP transports for maximum compatibility.
Requirements
- Node.js 20.19.0 or newer
- Access to a Prometheus server
- VS Code, Cursor, Windsurf, Claude Desktop or any other MCP client
Getting Started
First, install the Prometheus MCP server with your client. A typical configuration looks like this:
{
"mcpServers": {
"prometheus": {
"command": "npx",
"args": ["prometheus-mcp@latest", "stdio"],
"env": {
"PROMETHEUS_URL": "http://localhost:9090"
}
}
}
}
Configuration
Prometheus MCP server supports the following arguments. They can be provided in the JSON configuration above, as part of the "args" list:
> npx prometheus-mcp@latest --help
Commands:
stdio Start Prometheus MCP server using stdio transport
http Start Prometheus MCP server using HTTP transport
Options:
--help Show help [boolean]
--version Show version number [boolean]
Environment Variables
You can also configure the server using environment variables:
PROMETHEUS_URL- Prometheus server URLENABLE_DISCOVERY_TOOLS- Set to “false” to disable discovery tools (default: true)ENABLE_INFO_TOOLS- Set to “false” to disable info tools (default: true)ENABLE_QUERY_TOOLS- Set to “false” to disable query tools (default: true)
Standalone MCP Server
When running in server environments or when you need HTTP transport, run the MCP server with the http command:
npx prometheus-mcp@latest http --port 3000
And then in your MCP client config, set the url to the HTTP endpoint:
{
"mcpServers": {
"prometheus": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:3000/mcp"]
}
}
}
Docker
Run the Prometheus MCP server using Docker:
{
"mcpServers": {
"prometheus": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"--init",
"--pull=always",
"-e",
"PROMETHEUS_URL=http://host.docker.internal:9090",
"ghcr.io/idanfishman/prometheus-mcp",
"stdio"
]
}
}
}
Tools
The Prometheus MCP server provides 10 tools organized into three configurable categories:
Example Usage
Here are some example interactions you can have with your AI assistant:
Basic Queries
- “Show me all available metrics in Prometheus”
- “What’s the current CPU usage across all instances?”
- “Get the memory usage for the last hour”
Discovery and Exploration
- “List all scrape targets and their status”
- “What labels are available for the
http_requests_totalmetric?” - “Show me all metrics related to ‘cpu’”
Advanced Analysis
- “Compare CPU usage between production and staging environments”
- “Show me the top 10 services by memory consumption”
- “What’s the error rate trend for the API service over the last 24 hours?”
Security Considerations
- Network Access: The server requires network access to your Prometheus instance
- Resource Usage: Range queries can be resource-intensive; monitor your Prometheus server load
Troubleshooting
Connection Issues
- Verify your Prometheus server is accessible at the configured URL
- Check firewall settings and network connectivity
- Ensure Prometheus API is enabled (default on port 9090)
Permission Errors
- Verify the MCP server has network access to Prometheus
- Check if authentication is required for your Prometheus setup
Tool Availability
- If certain tools are missing, check if they’ve been disabled via configuration
License
This project is licensed under the MIT License - see the LICENSE file for details.
Support
- GitHub Issues: Report bugs or request features
- Documentation: Model Context Protocol Documentation
- Prometheus: Prometheus Documentation
Built with ❤️ for the Prometheus and MCP communities
Install
npx prometheus-mcp@latest stdioConfiguration
{
"mcpServers": {
"prometheus": {
"command": "npx",
"args": ["prometheus-mcp@latest", "stdio"],
"env": {
"PROMETHEUS_URL": "http://localhost:9090"
}
}
}
}