RAG MCP Server
MCP RAG con Python, LangChain, LangGraph y LlamaIndex
Proyecto de servidor Model Context Protocol (MCP) para indexar documentos y responder preguntas con RAG (Retrieval-Augmented Generation). El servidor usa FastMCP vía SSE, LlamaIndex + ChromaDB para recuperación, LangGraph para orquestación y LangChain para generación.
Arquitectura
Cliente MCP -> SSE (/sse) -> FastMCP
-> ingest_documents(paths)
-> ask_rag(question)
-> LangGraph
-> recuperar contexto (LlamaIndex/Chroma)
-> gerar resposta (LangChain/OpenAI)
-> validar citaçõesRelated MCP server: Antigravity PDF MCP Server
Inicio rápido
cp .env.example .env
# Edite .env e informe OPENAI_API_KEY
docker compose up --buildEl endpoint MCP SSE está en http://localhost:8000/sse.
Documentos
Para hacer que una carpeta local esté disponible para el contenedor, descomenta el volumen ./docs:/workspace/docs:ro en el docker-compose.yml. Luego, llama a la herramienta con una ruta como /workspace/docs/manual.md.
Herramientas MCP
ingest_documents
Indexa archivos .txt, .md y .pdf.
{"paths": ["/workspace/docs/manual.md"]}ask_rag
Recupera los fragmentos más relevantes y responde con referencias [S1], [S2].
{"question": "Quais são os procedimentos de backup?", "top_k": 5}Variables de entorno
Variable | Uso |
| Clave de la API compatible con OpenAI |
| Modelo de generación LangChain |
| Modelo de embeddings LlamaIndex |
| URL base opcional de endpoint compatible |
| Directorio persistente de ChromaDB |
| Nombre de la colección vectorial |
| Tamaño de los fragmentos indexados |
| Superposición entre fragmentos |
Seguridad
No expongas el SSE públicamente sin TLS y autenticación. Monta solo directorios de documentos autorizados, ya que la herramienta de ingestión lee las rutas indicadas.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables RAG (Retrieval-Augmented Generation) capabilities with document processing, vector storage, and intelligent Q\&A using OpenAI embeddings and semantic search.
- FlicenseNot gradedqualityDmaintenanceEnables intelligent ingestion and querying of PDF, Markdown, and text files using hybrid search that combines keyword matching and semantic embeddings with citations.2
- AlicenseNot gradedqualityDmaintenanceEnables uploading, organizing, and semantically searching documents with support for various file types and embedding providers.27MIT
- AlicenseNot gradedqualityDmaintenanceEnables document Q&A with grounded citations using the official Gemini File Search API. Upload documents, create stores, and ask questions that return exact passage citations.162MIT
Related MCP Connectors
Your company's brain for AI agents. Cited, permission-aware knowledge across every system.
Citable retrieval across papers, books, patents, Wikipedia, and live social sources.
Search and reason over your Obsidian-style Markdown vault, right from ChatGPT.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/johnylira/servidor_mcp_completo_python'
If you have feedback or need assistance with the MCP directory API, please join our Discord server