mcp-documentation-server MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

Local-first: no cloud DB, no external calls unless you enable Gemini
Parent-child chunking balances precision and context
Hybrid full-text + vector search
Built-in web dashboard on port 3080 for drag-and-drop uploads
Supports .txt, .md, and .pdf out of the box

Demo ao vivo

Como fica na prática

documentation-server.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "documentation-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ],
      "_inferred": true
    }
  }
}

Abra Claude Desktop → Settings → Developer → Edit Config. Reinicie após salvar.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "documentation-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ],
      "_inferred": true
    }
  }
}

Cursor usa o mesmo esquema mcpServers que o Claude Desktop. Config de projeto vence a global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "documentation-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ],
      "_inferred": true
    }
  }
}

Clique no ícone MCP Servers na barra lateral do Cline, depois "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "documentation-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ],
      "_inferred": true
    }
  }
}

Mesmo formato do Claude Desktop. Reinicie o Windsurf para aplicar.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "documentation-server",
      "command": "npx",
      "args": [
        "-y",
        "mcp-documentation-server"
      ]
    }
  ]
}

O Continue usa um array de objetos de servidor em vez de um map.

~/.config/zed/settings.json

{
  "context_servers": {
    "documentation-server": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-documentation-server"
        ]
      }
    }
  }
}

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

claude mcp add documentation-server -- npx -y mcp-documentation-server

Uma linha só. Verifique com claude mcp list. Remova com claude mcp remove.

Casos de uso

Usos do mundo real: mcp-documentation-server

Make a new framework's docs queryable by your AI

👤 Devs adopting a new library ⏱ ~20 min beginner

Quando usar: Official docs are huge; you want Claude to answer with grounded citations.

Pré-requisitos

mcp-documentation-server installed — npx -y @andrea9293/mcp-documentation-server

Fluxo

Ingest the docs

Upload the library's docs .md files to the dashboard at http://localhost:3080.✓ Copiado

→ Files processed into chunks
Ask targeted questions

search_documents for 'how to configure middleware' — give me the top 3 chunks with source paths.✓ Copiado

→ Cited excerpts
Ask grounded synthesis

Given those chunks, write the minimum viable config for middleware in this framework.✓ Copiado

→ Working config backed by cited doc lines

Resultado: A personal docs assistant that cites its sources.

Armadilhas

PDFs with scanned images aren't OCR'd — Pre-OCR with tools like ocrmypdf before upload
Huge doc sets without Gemini give noisy embeddings — Optional GEMINI_API_KEY unlocks higher-quality semantic search

Combine com: filesystem

Turn an internal wiki export into a RAG source

👤 Teams with markdown-export-friendly wikis ⏱ ~25 min beginner

Quando usar: You've exported your Notion/Confluence content as Markdown and want AI access.

Fluxo

Bulk-ingest via process_uploads

process_uploads on ./wiki-export/ — process every .md.✓ Copiado

→ Document count per folder
Full-scope search

search_all_documents: 'deployment runbook' — top 5.✓ Copiado

→ Ranked list

Resultado: A local, private, searchable wiki.

Build a personal research-paper library

👤 Researchers, students ⏱ ~30 min beginner

Quando usar: You download papers and want them queryable instead of piled in Downloads/

Fluxo

Drop PDFs in

Upload all PDFs in ~/Papers/ to the documentation server.✓ Copiado

→ Papers chunked and indexed
Ask across corpus

search_documents: 'attention variants with lower quadratic cost' — return authors + years.✓ Copiado

→ Cited excerpts

Resultado: A local mini-perplexity over your own paper collection.

Combinações

Combine com outros MCPs para 10× de alavancagem

documentation-server + filesystem

Automate ingest from a watched folder

Every time a new PDF lands in ~/Papers/Inbox, process_uploads it into the documentation server.✓ Copiado

documentation-server + swarmvault

Compare: documentation-server is quick-ingest; swarmvault builds a structured wiki

Ingest my research PDFs into both systems; compare retrieval quality on the same query.✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
add_document	title, content, metadata?	Programmatic ingest	free (local embeddings)
list_documents	(none)	See what's indexed	free
get_document	id	Retrieve a specific doc	free
delete_document	id	Pruning	free
search_documents	query, top_k?	Query within a specific doc set	free
search_all_documents	query, top_k?	Global RAG query	free
get_context_window	chunk_id	Expand a narrow hit into broader context	free
search_documents_with_ai	query	One-shot answer synthesis	Gemini call (needs key)
process_uploads	path?: str	Batch import from the uploads folder	free

Custo e limites

O que custa rodar

Cota de API: None if local; Gemini usage if GEMINI_API_KEY set
Tokens por chamada: Search returns 500-3000 tokens depending on top_k
Monetário: Free; Gemini is paid per-call if enabled
Dica: Skip Gemini for exploratory work — local embeddings are good enough for known-item lookups.

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: GEMINI_API_KEY (optional) in env

Saída de dados: Local only unless Gemini is enabled; dashboard on port 3080

Dashboard on :3080 has no auth — bind to localhost only.
Document content sits in the MCP_BASE_DIR as JSON; treat it like any local data.

Solução de problemas

Erros comuns e correções

Port 3080 in use

Set WEB_PORT env var to another port.

Verificar: lsof -i :3080

PDF parse error

Password-protected or scanned PDFs fail. Remove password or run OCR first.

Verificar: Try a plain PDF

search returns empty

Check documents ingested: list_documents. If empty, re-run process_uploads.

Verificar: list_documents

Alternativas

mcp-documentation-server vs. outros

Alternativa	Quando usar	Troca
swarmvault	You want a structured wiki + knowledge graph, not just search	Heavier; more upfront setup
Cloud RAG (Pinecone, Weaviate)	You need team-shared, scale	Paid; data leaves your machine
llm-context.py	You want per-task context, not persistent doc retrieval	Different problem

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills