MCP.so
Sign In

Langfuse MCP

@therealsachin

Repository

About Langfuse MCP

Production-ready Langfuse MCP Server with 28 tools for LLM analytics, cost monitoring, and dataset management. Features secure dual-mode operation (readonly & readwrite), real-time cost analysis, trace debugging, and comprehensive usage insights. Deploy instantly with npx for sea

#langfuse#analytics#llm#cost-monitoring#tracing#observability#datasets#ai-tools#production#debugging

Basic information

Category

Data & Analytics

Transports

stdio

Publisher

therealsachin

Submitted by

Sachin Shenoy

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "langfuse-mcp": {
      "command": "npx",
      "args": [
        "langfuse-mcp"
      ],
      "env": {
        "LANGFUSE_SECRET_KEY": "<YOUR_LANGFUSE_SECRET_KEY>",
        "LANGFUSE_PUBLIC_KEY": "<YOUR_LANGFUSE_PUBLIC_KEY>",
        "LANGFUSE_HOST": "<YOUR_LANGFUSE_URL>"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Langfuse MCP?

Comprehensive MCP server providing 28 powerful tools for Langfuse analytics, cost monitoring, and dataset management. Built for production environments with enterprise-grade security features.

How to use Langfuse MCP?

Run npx @therealsachin/langfuse-mcp --readwrite with environment variables LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, and LANGFUSE_BASEURL. Alternatively install globally via npm and run with --readonly or set the LANGFUSE_MCP_MODE environment variable.

Key features of Langfuse MCP

  • Real-time analytics: cost analysis, usage tracking, trace debugging
  • Dual security modes: readonly (default) and readwrite with audit logging
  • Dataset management: complete CRUD operations for training datasets
  • Advanced debugging: trace details, observation analysis, model insights
  • Cost optimization: usage by model/service, expensive trace identification
  • Production security: HTTPS validation, pre-commit hooks, credential scanning

Use cases of Langfuse MCP

  • AI teams managing LLM costs and performance
  • DevOps engineers monitoring production AI systems
  • Data scientists analyzing model usage patterns
  • Product teams optimizing AI feature costs

FAQ from Langfuse MCP

What security modes does Langfuse MCP support?

Langfuse MCP supports two modes: readonly (safe default) and readwrite (requires explicit --readwrite flag). Audit logging and HTTPS enforcement are included.

What environment variables are required to run Langfuse MCP?

You need LANGFUSE_PUBLIC_KEY, LANGFUSE_SECRET_KEY, and optionally LANGFUSE_BASEURL (defaults to https://us.cloud.langfuse.com).

How can I install Langfuse MCP?

You can run it via npx (npx @therealsachin/langfuse-mcp) or install globally with npm (npm install -g @therealsachin/langfuse-mcp).

How does Langfuse MCP ensure production security?

It enforces HTTPS to prevent credential leaks, provides pre-commit hooks with Gitleaks integration for credential scanning, and logs all write operations for audit.

Comments

More Data & Analytics MCP servers

Deep Research

u14app

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

4.6K

MCP Deep Web Research Server (v0.3.0)

qpd-v

Enhanced MCP server for deep web research

86

MCP Server for Data Exploration

reading-plus-ai

544

HubSpot MCP Server

baryhuang

A Model Context Protocol (MCP) server that enables AI assistants to interact with HubSpot CRM data, providing built-in vector storage and caching mechanisms help overcome HubSpot API limitations while improving response times.

128

arxiv-latex MCP Server

takashiishida

MCP server that uses arxiv-to-prompt to fetch and process arXiv LaTeX sources for precise interpretation of mathematical expressions in scientific papers.

140