Protocolo de Contexto de Modelo: Temas Avanzados

Resumen

Go beyond MCP basics with sampling, notifications, roots, and the STDIO and StreamableHTTP transports in Python. You've built an MCP server that exposes a few tools - now it's time to make it behave like the ones running in production.

Advanced MCP is where servers delegate work to clients, report on what they're doing, respect filesystem boundaries, and talk to clients across very different transports. Master Core MCP Features Start with sampling, which lets a server hand a prompt back to the client's language model instead of holding its own API key.

Then stream log and progress notifications so learners watching a 30-second tool call can see it working, and use roots to define exactly which files and folders a server is allowed to touch - a boundary the SDK leaves you to enforce yourself. Understand How Clients and Servers Talk Go to the wire level and see what actually crosses the connection.

You'll hand-write JSON-RPC requests and notifications, tell the two apart by their id field, and follow the initialization handshake message by message. Compare the STDIO and StreamableHTTP Transports Learn why a STDIO server only works on one machine, how the StreamableHTTP transport uses a long-lived Server-Sent Events stream to push messages back to the client, and what the stateless_http and json_response flags trade away.

By the end, you'll know which transport fits a local tool versus a remote, load-balanced deployment - and why.

Programa

• Características principales de MCP
Descubre las características avanzadas que separan un servidor MCP de juguete de uno de producción. Usarás el muestreo para tomar prestado el modelo de lenguaje del cliente, transmitirás registros y notificaciones de progreso desde una herramienta lenta para que los usuarios vean que está funcionando, y aplicarás raíces para que un servidor solo toque los archivos que se le otorgaron.
• Transportes y comunicación
Ve al nivel de cableado y observa cómo los clientes y servidores MCP realmente se comunican. Escribirás a mano solicitudes y notificaciones JSON-RPC, rastrearás el apretón de manos de inicialización y compararás el transporte STDIO para servidores locales con el transporte StreamableHTTP para servidores remotos, incluyendo cómo los Eventos Enviados por el Servidor y la falta de estado influyen en lo que cada uno puede hacer.

---

Impartido por

Anthropic Academy

---

Materias

Artificial Intelligence