MCP Server for langfuse

A Model Context Protocol (MCP) server implementation for integrating AI assistants with Langfuse workspaces.

Overview

This package provides an MCP server that enables AI assistants to interact with Langfuse workspaces. It allows AI models to:

Query LLM Metrics by Time Range

Installation

# Install from npm
npm install shouting-mcp-langfuse

# Or install globally
npm install -g shouting-mcp-langfuse

You can find the package on npm: shouting-mcp-langfuse

Prerequisites

Before using the server, you need to create a Langfuse project and obtain your project's public and private keys. You can find these keys in the Langfuse dashboard.

set up a Langfuse project
get the public and private keys
set the environment variables

Configuration

The server requires the following environment variables:

LANGFUSE_DOMAIN: The Langfuse domain (default: https://api.langfuse.com)
LANGFUSE_PUBLIC_KEY: Your Langfuse Project Public Key
LANGFUSE_PRIVATE_KEY: Your Langfuse Project Private Key

Usage

Running as a CLI Tool

# Set environment variables
export LANGFUSE_DOMAIN="https://api.langfuse.com"
export LANGFUSE_PUBLIC_KEY="your-public-key"
export LANGFUSE_PRIVATE_KEY="your-private

# Run the server
mcp-server-langfuse

Using in Your Code

import { Server } from "@modelcontextprotocol/sdk/server/index.js";
import { langfuseClient } from "shouting-mcp-langfuse";

// Initialize the server and client
const server = new Server({...});
const langfuseClient = new LangfuseClient(process.env.LANGFUSE_DOMAIN, process.env.LANGFUSE_PUBLIC_KEY, process.env.LANGFUSE_PRIVATE_KEY);

// Register your custom handlers
// ...