Langfuse MCP Server
Agent-facing Model Context Protocol server and skill for Langfuse observability.
Use langfuse-mcp from Claude Code, Codex, Cursor, or any MCP client to query traces, inspect generations, debug exceptions, analyze sessions, manage prompts, browse datasets, and understand what your AI agents did in production.
What You Can Do
- Debug failing agent runs from Langfuse traces and observations.
- Find exceptions, slow generations, high-latency spans, and affected users.
- Inspect sessions and user journeys without leaving your agent workflow.
- Manage prompt versions, labels, datasets, annotation queues, and scores.
- Install the included
langfuseagent skill for ready-made debugging playbooks.
Project Links
- Quick Start
- Agent Skill
- Tools
- Selective Tool Loading
- Read-Only Mode
- Other Clients
Why langfuse-mcp?
Langfuse is where your traces live. langfuse-mcp makes that telemetry directly usable by agents that need to answer questions like "what failed?", "why was this slow?", "which prompt version ran?", or "what happened in this user's session?"






