langfuse-mcp

MCP server that exposes the Langfuse REST API as tools — query traces, observations, sessions, scores, prompts, datasets, and metrics from any MCP client.

Monitoring & Observability

Install Command

npx -y langfuse-mcp

Claude Desktop Config

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

langfuse-mcp is a community MCP server that connects AI assistants like Claude to mcp server that exposes the langfuse rest api as tools — query traces, observations, sessions, scores, prompts, datasets, and metrics from any mcp client. It runs locally on your machine, keeping your data private and giving you full control over the connection. Adding it to your setup expands what Claude can do without any extra coding.

About langfuse-mcp

Overview

MCP server that exposes the Langfuse REST API as tools — query traces, observations, sessions, scores, prompts, datasets, and metrics from any MCP client.

Topics

langfuse, mcp, mcp-server, model-context-protocol, llm-observability, observability, traces, observations, prompts, datasets, evals, claude, anthropic, cursor, tracing, ai

Who Should Use langfuse-mcp?

1Extend Claude and other AI assistants with new capabilities
2Automate tasks that previously required manual steps
3Connect your existing tools to an AI workflow
4Reduce repetitive work by letting AI interact with your services

How to Install langfuse-mcp

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.