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., "@MCP Study Agent generate study flashcards for architecture.txt"
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.
Este proyecto implementa un agente MCP (Model Context Protocol) capaz de interactuar con documentos locales para facilitar el estudio.
Clonar/Abrir el proyecto en VS Code.
Crear y activar entorno virtual:
python -m venv venv
.\venv\Scripts\activateInstalar dependencias:
pip install -r requirements.txtRelated MCP server: Docalyze
Corre el servidor FastAPI usando Uvicorn:
uvicorn mcp-server.server:app --reloadEl servidor estará disponible en: http://127.0.0.1:8000
Muestra los archivos disponibles en la carpeta data/.
URL: GET /tools/list_documents
Lee el contenido de un archivo específico.
URL: GET /tools/read_document?filename=prueba.txt
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
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.
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.
El servidor MCP se ejecuta localmente usando uvicorn.
El servidor expone herramientas MCP que pueden ser usadas por el agente.
El agente invoca la tool read_document y genera un resumen del documento.
This server cannot be deployed
The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
MCP server for agentverse documentation, generated by doc2mcp.
The Needle MCP server enables semantic search on documents stored in files like PDFs, DOCX, and XLSX by connecting AI applications to external data sources. It provides capabilities to create and manage document collections, perform natural language searches on stored content, and retrieve relevant information without requiring exact keyword matches.
