Langfuse

Overview

Langfuse is a Model Context Protocol (MCP) server: MCP server for Langfuse LLM observability — trace and observation analysis. Because it speaks the Model Context Protocol, AI assistants can use Langfuse as a set of callable tools instead of you copy-pasting between apps.

It runs locally: the npm package langfuse-observability-mcp-server speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need LANGFUSE_SECRET_KEY, LANGFUSE_PUBLIC_KEY. The current release is v0.1.3, published under the MIT license, with source at pulsemcp/mcp-servers on GitHub, where it has earned 80 stars.

On mcp.site, Langfuse sits in the AI & Agents category. Any MCP client can use it — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed among them — via the install snippets below. If you maintain Langfuse for pulsemcp.com, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "langfuse": {
      "command": "npx",
      "args": [
        "-y",
        "langfuse-observability-mcp-server"
      ],
      "env": {
        "LANGFUSE_SECRET_KEY": "<langfuse-secret-key>",
        "LANGFUSE_PUBLIC_KEY": "<langfuse-public-key>"
      }
    }
  }
}

Requires LANGFUSE_SECRET_KEY, LANGFUSE_PUBLIC_KEY