Demo MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Demo MCP Serversuma 5 y 7"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Demo: servidor MCP + LLM mockeado
Ejemplo mínimo del protocolo MCP (Model Context Protocol) con:
server.py: servidor MCP con dos tools (suma,clima).mock_llm.py: un "LLM" 100% falso, basado en reglas con regex, que decide qué tool llamar según el mensaje del usuario. No hace ninguna llamada a red ni a ninguna API real.client.py: cliente MCP que lanzaserver.pycomo subproceso, le pide la lista de tools, y usamock_llm.pypara decidir qué tool invocar y cómo redactar la respuesta final con el resultado.
Setup
python3.11 -m venv .venv
./.venv/bin/pip install -r requirements.txtRelated MCP server: MCP Boilerplate
Ejecutar
./.venv/bin/python client.pyPrueba en el propio client.py tres mensajes: una suma, una
consulta de clima y un mensaje sin match, para ver los tres caminos
(tool suma, tool clima, sin tool).
Sustituir el LLM mockeado por uno real
mock_llm.py expone la misma forma que necesitarías para conectar un LLM
real vía tool-calling (p. ej. Claude): recibe el mensaje del usuario y la
lista de tools, decide si llamar a una y con qué argumentos, y luego
redacta la respuesta final a partir del resultado de la tool. Cambiar
MockLLM por un cliente real (Anthropic, OpenAI, etc.) no requiere tocar
server.py ni la lógica de client.py que habla con MCP.
This server cannot be deployed
Maintenance
Related MCP Connectors
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA demonstration server for the Model Context Protocol (MCP) that exposes calculator and Yahoo Finance tools, allowing LLMs to interpret natural language requests and make tool calls via the MCP standard.1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceA minimal, production-ready MCP server with a simple addition calculator tool that demonstrates integration with the Model Context Protocol.4 npm1MIT
- FlicenseAqualityDmaintenanceA minimal MCP server demo written without the MCP Python SDK that demonstrates the complete protocol flow. It provides weather, file search, and datetime tools, and includes a CLI client that bridges MCP tools with OpenAI function calling.3-
- AlicenseNot gradedqualityDmaintenanceThis MCP server provides tools like weather lookup and follows the Model Context Protocol for tool calling, resource sharing, and prompt templates.221 npmMIT