concierge MCP — Casos de uso, Instalar & Demo en vivo

Por qué usarlo

Características clave

Progressive disclosure — only expose tools relevant to the current workflow step
Workflow state shared across steps without manual plumbing
Semantic tool search — worth it once you cross ~100 tools
Multiple transports: stdio, HTTP, SSE
Session-isolated — concurrent workflows don't clobber each other

Demo en vivo

Cómo se ve en la práctica

concierge.replay ▶ listo

0/0

Instalar

Elige tu cliente

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "concierge": {
      "command": "uvx",
      "args": [
        "concierge"
      ],
      "_inferred": true
    }
  }
}

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "concierge": {
      "command": "uvx",
      "args": [
        "concierge"
      ],
      "_inferred": true
    }
  }
}

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

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "concierge": {
      "command": "uvx",
      "args": [
        "concierge"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "concierge": {
      "command": "uvx",
      "args": [
        "concierge"
      ],
      "_inferred": true
    }
  }
}

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "concierge",
      "command": "uvx",
      "args": [
        "concierge"
      ]
    }
  ]
}

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

~/.config/zed/settings.json

{
  "context_servers": {
    "concierge": {
      "command": {
        "path": "uvx",
        "args": [
          "concierge"
        ]
      }
    }
  }
}

Añádelo a context_servers. Zed recarga en caliente al guardar.

claude mcp add concierge -- uvx concierge

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

Casos de uso

Usos del mundo real: concierge

Wrap a giant REST API (200+ endpoints) as an MCP without blowing the context

👤 Platform engineers exposing internal APIs to LLMs ⏱ ~90 min advanced

Cuándo usarlo: Your company's API has 300 endpoints and a naive MCP dumps all of them into the system prompt, wrecking latency and hit rate.

Requisitos previos

Python 3.9+ — pyenv / uv
OpenAPI spec or endpoint catalog — Your API gateway / Swagger

Flujo

Scaffold with concierge-sdk

Using concierge-sdk, scaffold an MCP server that wraps my OpenAPI spec at ./openapi.yaml. Make it use semantic search rather than listing all tools up front.✓ Copiado

→ Boilerplate code + search handler
Define workflow stages

Group the endpoints into 3 workflows: 'read operations', 'create operations', 'admin'. Each workflow exposes only its own tools.✓ Copiado

→ Workflow definitions with tool allowlists
Test with Claude

Connect Claude Desktop to this server and verify that listing tools only shows the search tool + current workflow tools — not all 300.✓ Copiado

→ Claude sees ~10 tools, not 300

Resultado: A large API surface usable by an LLM without collapsing on system prompt length.

Errores comunes

Semantic search returns the wrong tool when descriptions are too similar — Write distinctive one-line tool descriptions; test search with held-out queries

Build a guided multi-step workflow (e.g. customer onboarding)

👤 Devs building structured agent flows ⏱ ~60 min advanced

Cuándo usarlo: You want the LLM to follow a defined sequence: collect info → validate → create record → notify. Each step has its own tools.

Flujo

Declare the workflow

Define a concierge workflow 'customer_onboarding' with steps [collect, validate, create, notify], each with its own tool set.✓ Copiado

→ Workflow config
Share state

Pass the customer_data dict from step 1 into steps 2, 3, 4 via shared state. Show me how.✓ Copiado

→ State-object code
Handle failure

If validate fails, return to step 1 with the specific fix needed.✓ Copiado

→ Retry/backtrack logic

Resultado: A robust guided flow that keeps the LLM on-rails.

Errores comunes

LLM tries to skip steps — Concierge enforces order at the tool-visibility level — skipping is physically impossible if you wired it right

Ship your first MCP server in 15 minutes

👤 Developers new to MCP ⏱ ~15 min beginner

Cuándo usarlo: You want to expose 3-5 functions to Claude and don't want to learn the raw MCP spec.

Flujo

Install and scaffold

pip install concierge-sdk. Generate a minimal server exposing two tools: add(a, b) and greet(name). Stdio transport.✓ Copiado

→ Working Python file
Run and connect

Add to Claude Desktop config and test that both tools are callable.✓ Copiado

→ Tool calls succeed in Claude

Resultado: A working MCP server you wrote end-to-end in an afternoon.

Errores comunes

Missing type hints — SDK relies on them for tool schema — Always type your args and return — concierge generates the MCP schema from them

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

concierge + gateway

Serve concierge-built MCP behind a security gateway for PII redaction

Start concierge server on :8001, then add it as an upstream to mcp-gateway with Presidio plugin.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
concierge.workflow(name)	name, steps, initial_state	Define a named multi-step flow	framework only
concierge.tool(workflow, step)	step allowlist	Attach a function as a tool scoped to one or more steps	framework only
concierge.search_tools	query: str	Auto-exposed when you have too many tools to list eagerly	free
concierge.serve()	transport: 'stdio'\|'http'\|'sse'	Entry point of your script	free

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: None — you're the author
Tokens por llamada: Depends on your tool design; progressive disclosure shrinks system prompts 5-10x
Monetario: Free and open source
Consejo: Don't eagerly expose every tool. Start with 'search' + current-step tools. Add eager tools only if profiling shows the LLM always needs them.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: Your MCP server handles its own credentials — concierge doesn't impose a model

Salida de datos: Whatever your tools call

As an SDK, concierge's threat model is inherited from how you use it. Validate inputs in each tool.
Session isolation protects state per-user but shared external resources still need their own locks.

Resolución de problemas

Errores comunes y soluciones

Tools not appearing in the expected step

Check the step arg on @concierge.tool. A tool with step=['create'] is invisible during collect.

Verificar: Call the search_tools tool; if nothing returns, your allowlist is wrong

Semantic search returns no results

Tool descriptions may be empty. Concierge builds embeddings from docstrings — fill them in.

Workflow state lost between calls

Concierge state is session-scoped. Ensure your client is sticky (same MCP session across calls).

Alternativas

concierge vs otros

Alternativa	Cuándo usarla	Contrapartida
fastmcp (Python)	You want the most popular Python MCP SDK without progressive disclosure	Lighter, but no built-in workflow/tool-gating features
Official MCP Python SDK	You want zero framework, closest to the spec	More boilerplate; you build gating yourself
TypeScript MCP SDK	Your stack is TS/Node	Different language; no direct concierge equivalent

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills