What is Mcp Langfuse

mcp-langfuse is a Model Context Protocol (MCP) server implementation designed to integrate AI assistants with Langfuse workspaces, allowing AI models to query LLM metrics by time range.

Use cases

Use cases for mcp-langfuse include monitoring AI model performance over time, integrating AI assistants into existing workflows, and enhancing data-driven decision-making processes within organizations.

How to use

To use mcp-langfuse, first install it via npm. Set up a Langfuse project to obtain your public and private keys, then configure the necessary environment variables. You can run the server as a CLI tool or integrate it into your code using the provided SDK.

Key features

Key features of mcp-langfuse include the ability to query LLM metrics by time range and seamless integration with Langfuse workspaces, enabling AI assistants to effectively interact with the data.

Where to use

mcp-langfuse can be used in AI development environments, particularly where integration with Langfuse workspaces is required for managing and analyzing AI model performance metrics.

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.

1. set up a Langfuse project
2. get the public and private keys
3. 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
// ...

Available Tools

The server provides the following langfuse integration tools:

• getLLMMetricsByTimeRange: Get LLM Metrics by Time Range

License

ISC

Author

[email protected]

Repository

https://github.com/z9905080/mcp-langfuse