/ Directorio / Playground / Langfuse MCP
● Oficial langfuse ⚡ Instantáneo

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 qué usarlo

Características clave

Demo en vivo

Cómo se ve en la práctica

langfuse-mcp.replay ▶ listo
0/0

Instalar

Elige tu 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"
      ]
    }
  }
}

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

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

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

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

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

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

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

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

Continue usa un array de objetos de servidor en lugar de un mapa.

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

Añádelo a context_servers. Zed recarga en caliente al guardar.

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

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: Langfuse MCP

Iterate on a production prompt with traceable versions

👤 Prompt engineers ⏱ ~15 min intermediate

Cuándo usarlo: You want to A/B a prompt without leaving the chat.

Requisitos previos
  • Server/skill installed and authenticated — See repo README
Flujo
  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.

Errores comunes
  • Labels are mutable — Labels are mutable — moving 'production' to a new version is an instant rollout. Confirm before relabel.
Combinar con: filesystem

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

langfuse-mcp + filesystem

Pair with filesystem for complementary capabilities

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

Herramientas

Lo que expone este MCP

HerramientaEntradasCuándo llamarCoste
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

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API
See provider docs for rate limits
Tokens por llamada
Varies by tool
Monetario
See repo README for pricing details
Consejo
Cache tool results and avoid repeated identical calls.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: Use environment variables; never commit secrets
Salida de datos: Tool calls go to the provider's API as documented

Resolución de problemas

Errores comunes y soluciones

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 otros

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

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills