Langfuse MCP server

The MCP Server for Langfuse enables AI assistants to interact with Langfuse workspaces, allowing them to query LLM metrics by time range through the Model Context Protocol (MCP) implementation.

Installation

You can install the MCP server using npm:

# Install from npm
npm install shouting-mcp-langfuse

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

Prerequisites

Before using the server, you need to complete these setup steps:

1. Set up a Langfuse project
2. Get your project's public and private keys from the Langfuse dashboard
3. Configure the required 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

Running the Server

As a CLI Tool

To run the server as a standalone 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-key"

# Run the server
mcp-server-langfuse

In Your Code

You can also integrate the server into your own 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 MCP server for Langfuse provides the following integration tools:

• getLLMMetricsByTimeRange: Retrieve LLM metrics from your Langfuse workspace for a specified time period

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-server-langfuse" '{"command":"npx","args":["-y","shouting-mcp-langfuse"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "mcp-server-langfuse": {
            "command": "npx",
            "args": [
                "-y",
                "shouting-mcp-langfuse"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "mcp-server-langfuse": {
            "command": "npx",
            "args": [
                "-y",
                "shouting-mcp-langfuse"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect