/ Diretório / Playground / Langfuse MCP
● Oficial langfuse ⚡ Instantâneo

Langfuse MCP

por langfuse · langfuse/mcp-server-langfuse

Manage Langfuse LLM-observability prompts from your agent.

Langfuse is open-source LLM observability and prompt management. This MCP lets Claude read prompt versions, fetch traces, and update prompt templates — useful for prompt engineers who want their assistant to actually touch the prompt store.

Por que usar

Principais recursos

Demo ao vivo

Como fica na prática

langfuse-mcp.replay ▶ pronto
0/0

Instalar

Escolha seu cliente

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "langfuse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "langfuse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  }
}

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "langfuse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  }
}

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "langfuse-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  }
}

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "langfuse-mcp",
      "command": "npx",
      "args": [
        "-y",
        "@langfuse/mcp-server"
      ]
    }
  ]
}

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json
{
  "context_servers": {
    "langfuse-mcp": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "@langfuse/mcp-server"
        ]
      }
    }
  }
}

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

claude mcp add langfuse-mcp -- npx -y @langfuse/mcp-server

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: Langfuse MCP

Iterate on a production prompt with traceable versions

👤 Prompt engineers ⏱ ~15 min intermediate

Quando usar: You want to A/B a prompt without leaving the chat.

Pré-requisitos
  • Server/skill installed and authenticated — See repo README
Fluxo
  1. Pull the current production prompt
    Get the 'support-triage' prompt labeled 'production' from Langfuse.✓ Copiado
    → Current prompt text + version number
  2. Test a tweak
    Create version with my proposed change labeled 'staging'. Don't promote.✓ Copiado
    → New version saved, 'production' label untouched

Resultado: Versioned, reviewable prompt history.

Armadilhas
  • Labels are mutable — Labels are mutable — moving 'production' to a new version is an instant rollout. Confirm before relabel.
Combine com: filesystem

Combinações

Combine com outros MCPs para 10× de alavancagem

langfuse-mcp + filesystem

Pair with filesystem for complementary capabilities

Use this server together with filesystem to complete a multi-step task.✓ Copiado

Ferramentas

O que este MCP expõe

FerramentaEntradasQuando chamarCusto
get_prompt name, version|label Retrieve a prompt for inspection or copying 1 API call
create_prompt name, prompt_text, labels Save a new version 1 API call
list_traces user_id|session_id, limit Debug a specific user/session 1 API call

Custo e limites

O que custa rodar

Cota de API
See provider docs for rate limits
Tokens por chamada
Varies by tool
Monetário
See repo README for pricing details
Dica
Cache tool results and avoid repeated identical calls.

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: Use environment variables; never commit secrets
Saída de dados: Tool calls go to the provider's API as documented

Solução de problemas

Erros comuns e correções

401 Unauthorized

Create a project in Langfuse, generate a key pair, set LANGFUSE_PUBLIC_KEY and LANGFUSE_SECRET_KEY.

Verificar: get_prompt on a known name works
prompt not found

Prompts are project-scoped. Confirm LANGFUSE_HOST and that the prompt exists in the target project.

Verificar: Open the Langfuse UI for that project

Alternativas

Langfuse MCP vs. outros

AlternativaQuando usarTroca
comet-ml/opik-mcpYou already use Opik for tracingSimilar feature set; different vendor

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills