convez.ai
MCP ServerIntegração & APIsIntermediário
langfuse

MCP Server Langfuse

langfuse/mcp-server-langfuse

Acesse e gerencie prompts Langfuse via Model Context Protocol

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que integra o Langfuse Prompt Management ao Claude e outras ferramentas compatíveis com Model Context Protocol. Permite listar, recuperar e compilar prompts gerenciados no Langfuse diretamente através do MCP, com suporte a paginação e variáveis dinâmicas.

Instalação

$npx convez-ai langfuse/mcp-server-langfuse

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
176
Forks
38
Acompanhando
2
Saúde
37%
Último commit
há 1 ano
Versão
v0.0.1
Issues abertas
14
Contribuidores
1

Casos de uso

  • Integrar prompts centralizados do Langfuse em workflows Claude Desktop
  • Listar e recuperar prompts em produção com variáveis compiladas dinamicamente
  • Usar Langfuse como repositório único de prompts para múltiplos clientes MCP

Veredito

Implementação sólida de integração MCP que transforma Langfuse em fonte centralizada de prompts. Prático para times que já usam Langfuse, mas com limitações (apenas produção, sem descrições de variáveis) que podem restringir casos de uso mais complexos.

README

A tradução para o português deste README ainda está na fila.

Langfuse Prompt Management MCP Server

Model Context Protocol (MCP) Server for Langfuse Prompt Management. This server allows you to access and manage your Langfuse prompts through the Model Context Protocol.

Demo

Quick demo of Langfuse Prompts MCP in Claude Desktop (unmute for voice-over explanations):

https://github.com/user-attachments/assets/61da79af-07c2-4f69-b28c-ca7c6e606405

Features

MCP Prompt

This server implements the MCP Prompts specification for prompt discovery and retrieval.

  • prompts/list: List all available prompts

    • Optional cursor-based pagination
    • Returns prompt names and their required arguments, limitation: all arguments are assumed to be optional and do not include descriptions as variables do not have specification in Langfuse
    • Includes next cursor for pagination if there's more than 1 page of prompts
  • prompts/get: Get a specific prompt

    • Transforms Langfuse prompts (text and chat) into MCP prompt objects
    • Compiles prompt with provided variables

Tools

To increase compatibility with other MCP clients that do not support the prompt capability, the server also exports tools that replicate the functionality of the MCP Prompts.

  • get-prompts: List available prompts

    • Optional cursor parameter for pagination
    • Returns a list of prompts with their arguments
  • get-prompt: Retrieve and compile a specific prompt

    • Required name parameter: Name of the prompt to retrieve
    • Optional arguments parameter: JSON object with prompt variables

Development

npm install

# build current file
npm run build

# test in mcp inspector
npx @modelcontextprotocol/inspector node ./build/index.js

Usage

Step 1: Build

npm install
npm run build

Step 2: Add the server to your MCP servers:

Claude Desktop

Configure Claude for Desktop by editing claude_desktop_config.json

{
  "mcpServers": {
    "langfuse": {
      "command": "node",
      "args": ["<absolute-path>/build/index.js"],
      "env": {
        "LANGFUSE_PUBLIC_KEY": "your-public-key",
        "LANGFUSE_SECRET_KEY": "your-secret-key",
        "LANGFUSE_BASEURL": "https://cloud.langfuse.com"
      }
    }
  }
}

Make sure to replace the environment variables with your actual Langfuse API keys. The server will now be available to use in Claude Desktop.

Cursor

Add new server to Cursor:

  • Name: Langfuse Prompts
  • Type: command
  • Command:
    LANGFUSE_PUBLIC_KEY="your-public-key" LANGFUSE_SECRET_KEY="your-secret-key" LANGFUSE_BASEURL="https://cloud.langfuse.com" node absolute-path/build/index.js
    

Limitations

The MCP Server is a work in progress and has some limitations:

  • Only prompts with a production label in Langfuse are returned
  • All arguments are assumed to be optional and do not include descriptions as variables do not have specification in Langfuse
  • List operations require fetching each prompt individually in the background to extract the arguments, this works but is not efficient

Contributions are welcome! Please open an issue or a PR (repo) if you have any suggestions or feedback.

Ver o original no GitHub

Bom para

Relacionados