pdf-reader-mcp MCP — Casos de uso, Instalar & Demo ao vivo

Por que usar

Principais recursos

Single read_pdf tool — no tool-sprawl to navigate
Parallel page processing: 5-10× faster on large PDFs
Layout-preserving text order (Y-coordinate based)
Reads local files and URLs; extracts images as base64

Demo ao vivo

Como fica na prática

pdf-reader.replay ▶ pronto

0/0

Instalar

Escolha seu cliente

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

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

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

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "pdf-reader": {
      "command": "npx",
      "args": [
        "-y",
        "pdf-reader-mcp"
      ],
      "_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": {
    "pdf-reader": {
      "command": "npx",
      "args": [
        "-y",
        "pdf-reader-mcp"
      ],
      "_inferred": true
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

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

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

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "pdf-reader",
      "command": "npx",
      "args": [
        "-y",
        "pdf-reader-mcp"
      ]
    }
  ]
}

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

~/.config/zed/settings.json

{
  "context_servers": {
    "pdf-reader": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "pdf-reader-mcp"
        ]
      }
    }
  }
}

Adicione em context_servers. Zed recarrega automaticamente ao salvar.

claude mcp add pdf-reader -- npx -y pdf-reader-mcp

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

Casos de uso

Usos do mundo real: pdf-reader-mcp

How to review a contract PDF with Claude

👤 Legal ops, founders, PMs ⏱ ~20 min beginner

Quando usar: You need to understand what's in a 50-page contract and flag unusual clauses.

Fluxo

Read the full PDF

Use read_pdf on ./contracts/msa-acme.pdf. Extract text and metadata.✓ Copiado

→ Full text + author/title/date metadata
Ask for a structured summary

Summarize: parties, term, payment terms, IP, termination, unusual clauses. Quote the exact clause for each.✓ Copiado

→ Structured summary with quotes
Red-flag review

Compared to a standard SaaS MSA, what clauses are unusual or risky? Cite page numbers.✓ Copiado

→ Prioritized list of things to negotiate

Resultado: A 15-minute review instead of a 2-hour one — with citations.

Armadilhas

Scanned PDFs return empty text — pdf-reader needs a text layer; run ocrmypdf input.pdf output.pdf first

Digest a folder of research PDFs into a summary table

👤 Analysts, researchers ⏱ ~15 min beginner

Quando usar: You downloaded 30 whitepapers and need a skim-layer before deciding what to read deeply.

Fluxo

List PDFs

List all PDFs in ./papers/. For each, extract title and abstract.✓ Copiado

→ Table: filename, title, abstract
Classify and rank

Classify each paper into [relevant / tangential / skip]. Give a 1-line 'why'.✓ Copiado

→ Prioritized reading list

Resultado: A reading order based on content, not file name.

Combine com: filesystem

Extract structured data from invoice PDFs

👤 Finance, AP teams ⏱ ~20 min intermediate

Quando usar: You receive PDF invoices and want them as CSV or JSON for your books.

Fluxo

Extract per invoice

For each PDF in ./inbox/, extract: vendor, invoice_number, date, total, line_items[]. Return as JSON array.✓ Copiado

→ Structured JSON per invoice
Flag anomalies

Highlight any invoices with totals >$10k or with line items that don't add up✓ Copiado

→ Review queue

Resultado: Automated AP triage with human-in-the-loop for flags.

Combine com: google-sheets

Combinações

Combine com outros MCPs para 10× de alavancagem

pdf-reader + filesystem

Iterate over a PDF folder, write summaries alongside

For each PDF in ./papers/, write a corresponding .md summary in the same folder.✓ Copiado

pdf-reader + google-sheets

Invoice data straight into a Sheets ledger

Extract invoices from ./inbox/*.pdf and append one row per invoice to my 'AP' sheet.✓ Copiado

Ferramentas

O que este MCP expõe

Ferramenta	Entradas	Quando chamar	Custo
read_pdf	path: str (local or URL), options?: { pages?, include_images?, include_metadata? }	Any PDF ingest — single tool handles all operations	Local CPU only

Custo e limites

O que custa rodar

Cota de API: None — runs locally
Tokens por chamada: A 50-page doc is 20k-100k tokens
Monetário: Free
Dica: Use the pages option to limit extraction to the first N pages when prototyping

Segurança

Permissões, segredos, alcance

Armazenamento de credenciais: None

Saída de dados: Only when given HTTP URLs; local paths stay local

Solução de problemas

Erros comuns e correções

Empty text from a valid PDF

PDF is image-only. Run OCR first: ocrmypdf in.pdf out.pdf, then read

Verificar: Check metadata; if `producer` says 'Scanner', it's imaged

Out-of-memory on huge PDFs

Pass pages: [1, 50] to chunk; process in ranges

Garbled text / wrong reading order

Some PDFs use non-standard layouts. Try disabling layout-preservation for raw stream order

Alternativas

pdf-reader-mcp vs. outros

Alternativa	Quando usar	Troca
mcp-server-pdf (simple)	Minimal dependency, okay with slower single-threaded	Much slower on large docs
LlamaParse API	You need LLM-grade layout understanding of complex forms/tables	Paid, cloud, better on messy docs

Mais

Recursos

📖 Leia o README oficial no GitHub

🐙 Ver issues abertas

🔍 Ver todos os 400+ servidores MCP e Skills