TODO list MCP server (Exercício 4.2)
Local MCP server that exposes tools for a TODO list, acting as an adapter between an AI agent and a REST API (localhost:8000).
README
MCP server da TODO list — Exercício 4.2
Um MCP server local que expõe tools de uma lista de tarefas para um agente
de IA. As tools não guardam estado próprio: elas chamam a API REST do
Exercício 4.1 (http://localhost:8000). O MCP é a camada de adaptação entre o
mundo do agente (MCP) e a fonte do dado (HTTP).
Aluno: Antonio Diniz · Disciplina: IDP-TD 2026
Agente / LLM ──MCP──▶ servidor_mcp.py ──HTTP──▶ API 4.1 (localhost:8000)
Tools expostas
| Tool | Chamada HTTP | Retorno |
|---|---|---|
criar_tarefa(titulo) |
POST /tarefas |
a tarefa criada {id, titulo, concluida} |
listar_tarefas() |
GET /tarefas |
lista de tarefas |
A URL da API é lida da variável de ambiente API (default http://localhost:8000).
Como rodar
-
Suba a API do 4.1 (noutro terminal, no repo do 4.1):
uvicorn app.main:app --port 8000 -
No repo do 4.2:
pip install -r requirements.txt python cliente_teste.pyDeve imprimir o envelope JSON com
tools,criar_resultadoelistar_resultado.
Para testar apontando para outra porta:
API=http://localhost:9010 python cliente_teste.py.
Reflexão (Aula 6)
No 4.1 o cliente precisava falar HTTP: montar URL, método, cabeçalhos, corpo e
tratar status. No 4.2 o agente só precisa saber que existe criar_tarefa(titulo).
O MCP escondeu o protocolo HTTP — endpoint, verbo, formato do corpo e códigos
de status deixaram de importar para quem chama. A tool virou a interface; a API
continua sendo a fonte do dado.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.