mcp-documentacao

mcp-documentacao

MCP server that indexes technical documents and provides hybrid search (vector + BM25) for retrieval only, without generation.

Category
Visit Server

README

mcp-documentacao

MCP server que indexa documentos técnicos e disponibiliza busca via RAG híbrida (vetorial + BM25). Apenas recuperação — sem geração.

Uso

pip install .
python3 src/server.py

O servidor roda via stdio — compatível com qualquer cliente MCP.

Configuração

Edite config.yaml:

sources:
  - path: ./src/guides
    type: documento
    description: Documentos técnicos

db_path: ./chroma_db
collection_name: documents

embedding:
    provider: huggingface   # huggingface | openai | jina | ollama
    model: paraphrase-multilingual-MiniLM-L12-v2

search:
    top_k: 5
    hybrid: true
    cache_max_size: 200
    cache_ttl: 3600

chunking:
    max_size: 1000
    overlap: 200

CONFIG_PATH pode ser passada como variável de ambiente.

Ferramentas MCP

Ferramenta Descrição
buscar_documentacao(pergunta, limite?, fonte?) Busca trechos relevantes
listar_documentos() Lista documentos indexados
reindexar() Reindexa todas as fontes

O parâmetro fonte filtra por tipo de fonte (ex: documento, faq).

Fontes

Múltiplas fontes com tipos arbitrários. Formatos suportados: Markdown (.md) e texto (.txt). Frontmatter YAML é lido como metadados (descrição, palavras-chave).

Docker

docker compose up --build

Monte volumes para /app/src/guides e /app/chroma_db para persistência.

Testes

pip install pytest
pytest tests/

Provedores de embedding

  • huggingface (padrão, local) — all-MiniLM-L6-v2, paraphrase-multilingual-MiniLM-L12-v2
  • openai — text-embedding-3-small, text-embedding-3-large (requer OPENAI_API_KEY)
  • jina — jina-embeddings-v3 (requer JINA_API_KEY)
  • ollama — modelos locais via Ollama

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
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

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