MCP Study Agent MCP Server

Local setup required. This server has to be cloned and prepared on your machine before you register it in Claude Code.
1

Set the server up locally

Run this once to clone and prepare the server before adding it to Claude Code.

Run in terminal
pip install -r requirements.txt
uvicorn mcp-server.server:app --reload
2

Register it in Claude Code

After the local setup is done, run this command to point Claude Code at the built server.

Run in terminal
claude mcp add mcp-study-agent -- node "<FULL_PATH_TO_MCP_STUDY_AGENT>/dist/index.js"

Replace <FULL_PATH_TO_MCP_STUDY_AGENT>/dist/index.js with the actual folder you prepared in step 1.

README.md

An MCP server to interact with local documents for educational purposes.

MCP Study Agent Project 📚

Este proyecto implementa un agente MCP (Model Context Protocol) capaz de interactuar con documentos locales para facilitar el estudio.

🚀 Instalación y Setup

  1. Clonar/Abrir el proyecto en VS Code.
  2. Crear y activar entorno virtual:
    python -m venv venv
    .\venv\Scripts\activate
    
  3. Instalar dependencias:
    pip install -r requirements.txt
    

🛠️ Ejecución del Servidor

Corre el servidor FastAPI usando Uvicorn:

uvicorn mcp-server.server:app --reload

El servidor estará disponible en: http://127.0.0.1:8000


🤖 Endpoints y Tools

1. Listar Documentos (Tool MCP)

Muestra los archivos disponibles en la carpeta data/.

  • URL: GET /tools/list_documents

2. Leer Documento (Tool MCP)

Lee el contenido de un archivo específico.

  • URL: GET /tools/read_document?filename=prueba.txt

3. Agente de Estudio (Agentic Flow)

Invoca al agente para procesar un documento usando las tools MCP.

  • URL: POST /agent/study
  • Body (JSON):
    {
      "filename": "arquitectura.txt",
      "mode": "summary"
    }
    
  • Modos disponibles: summary | flashcards

🧠 Estructura del Agente

  • Skills: Lógica de procesamiento de resúmenes y generación de flashcards en skills/study_skill.py.
  • Agente: El "cerebro" que decide invocar la tool read_document en agent/study_agent.py.
  • Server: Expone las herramientas y el punto de entrada para el agente.

✅ Checklist de Cumplimiento

  • Tools MCP: Funcionando y parametrizadas.
  • Skill: Pasos definidos para resumen y flashcards.
  • Agente: Invoca tools reales y entrega resultados útiles.
  • README: Guía de uso rápido.

Prueba de funcionamiento

Servidor corriendo

El servidor MCP se ejecuta localmente usando uvicorn.

Servidor corriendo


Tools disponibles

El servidor expone herramientas MCP que pueden ser usadas por el agente.

Tools MCP


Ejecución del agente

El agente invoca la tool read_document y genera un resumen del documento.

Resultado del agente

Tools (3)

list_documentsLists all files available in the local data directory.
read_documentReads the content of a specific file.
study_agentInvokes the agent to process a document for summaries or flashcards.

Configuration

claude_desktop_config.json
{"mcpServers": {"study-agent": {"command": "uvicorn", "args": ["mcp-server.server:app"]}}}

Try it

List all the documents available in my study folder.
Read the content of the file named architecture.txt.
Generate a summary for the document named architecture.txt.
Create study flashcards based on the content of my notes file.

Frequently Asked Questions

What are the key features of MCP Study Agent?

Lists local documents from a dedicated data directory. Reads and retrieves content from local text files. Automated generation of document summaries. Automated creation of study flashcards from documents.

What can I use MCP Study Agent for?

Summarizing long educational documents or lecture notes. Creating quick flashcards for exam preparation from local text files. Organizing and reviewing study materials stored locally.

How do I install MCP Study Agent?

Install MCP Study Agent by running: pip install -r requirements.txt && uvicorn mcp-server.server:app --reload

What MCP clients work with MCP Study Agent?

MCP Study Agent works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep MCP Study Agent docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare