knowledge-engine

knowledge-engine

MCP server for querying a personal knowledge base using semantic RAG, powered by DeepSeek and local embeddings from Ollama.

Category
Visit Server

README

Knowledge Engine

Motor de conocimiento personal con RAG semántico y servidor MCP, optimizado para el ecosistema DeepSeek.

Stack

Componente Tecnología Coste Motivo
Notas Obsidian (Markdown) Gratis Edición local
Embeddings Ollama + nomic-embed-text Gratis Ya lo tienes instalado; sin API externa
Vector DB ChromaDB (local) Gratis Sin servidor externo
Chat/LLM DeepSeek V4 Flash Muy bajo $0.14 input / $0.28 output por 1M tokens
Protocolo agentes MCP Gratis Estándar abierto

Configuración rápida

  1. Copia .env.example a .env y añade tu DEEPSEEK_API_KEY
  2. Crea un entorno virtual: python3 -m venv venv
  3. Actívalo: source venv/bin/activate (Unix) o venv\Scripts\activate (Windows)
  4. Instala dependencias: pip install -r requirements.txt
  5. Ejecuta python build_index.py para indexar tus notas por Ollama
  6. Consulta con python ask.py "tu pregunta"
  7. Usa python mcp_server.py para exponer la herramienta MCP a agentes externos

Optimización de costes

  • Usa deepseek-v4-flash (modelo por defecto): es el más económico.
  • Aprovecha su contexto de 1M tokens: puedes recuperar hasta 50+ fragmentos en una sola llamada.
  • max_tokens=1024 por defecto: limita el gasto por respuesta.
  • temperature=0: respuestas deterministas, más cortas y predecibles.
  • Los embeddings son gratis porque se generan en tu máquina con Ollama y nomic-embed-text.
  • Solo pagas por las consultas que haces, no por tener el sistema encendido.

Modelos disponibles

Modelo Precio input/output Contexto Uso recomendado
deepseek-v4-flash $0.14 / $0.28 por 1M tokens 1M Por defecto, alto volumen
deepseek-v4-pro $0.435 / $0.87 por 1M tokens 1M Razonamiento complejo

Cambia el modelo en .env si necesitas más calidad.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured