langfuse
MCP server for Langfuse LLM observability — trace and observation analysis.
Open the source (opens github.com) https://github.com/pulsemcp/mcp-servers
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY. Use a key with the least access you can.
What it is
MCP servers from com.pulsemcp.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
npm package (stdio)
langfuse-observability-mcp-server@0.1.3
From the server's entry in the official MCP Registry
Settings it asks for
LANGFUSE_SECRET_KEYsecret required · Langfuse secret key for authentication.LANGFUSE_PUBLIC_KEYsecret required · Langfuse public key for authentication.LANGFUSE_BASE_URL· Langfuse API base URL.
Related
-
Langfuse MCP
MCP serversLangfuse MCP server for accessing and analyzing telemetry data via natural language
langfuse-mcp@0.14.0 -
Langfuse API
MCP serversLangfuse public API (Cloud and self-hosted): traces, prompts, datasets and gated writes.
langfuse-api-mcp@0.2.0 -
ai-tutorial
MCP servers中文 AI 应用实战教程(含英文版):AgentScope Java、MCP、RAGFlow、FastGPT、Langfuse、LiteLLM、CopilotKit,本机实测,在线阅读与源码同仓。Hands-on Chinese AI tutorials (English edition available) covering AgentScope Java, MCP, RAGFlow, FastGPT, Langfuse, LiteLLM, and CopilotKit.
git clone https://github.com/ybak/ai-tutorial.git -
Production-ready RAG + MCP demo: eval-in-CI merge gate, Langfuse traces, structure-aware chunking.
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.