VaultPDF MCP
AlexeySamosadov/vaultpdf-mcp
Ferramentas PDF locais e privadas para agentes AI — sem upload de arquivos
Ver no GitHubServidor MCP que fornece ferramentas de manipulação de PDF para agentes de IA, executadas localmente na máquina do usuário. Oferece merge, split, conversão de imagens para PDF e obtenção de informações, com segurança de privacidade garantida — nenhum arquivo sai da máquina. Versão Pro desbloqueável com licença única em crypto.
Instalação
npx convez-ai AlexeySamosadov/vaultpdf-mcp1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Mesclar múltiplos PDFs em um único documento
- Extrair páginas específicas de um PDF
- Converter imagens JPG/PNG em PDF
- Obter metadados e dimensões de páginas
- Adicionar marca d'água, rotacionar e deletar páginas (Pro)
Veredito

MCP server sólido e bem-pensado para automação de PDFs com foco em privacidade. A arquitetura local + licença crypto é diferenciada, mas o modelo freemium com pagamento em USDC pode limitar adoção em certos contextos empresariais.
README
A tradução para o português deste README ainda está na fila.
VaultPDF MCP 🔒
Local PDF tools for AI agents. An MCP server that lets Claude, ChatGPT Apps, or any MCP host work with PDFs on the user's own machine — files are never uploaded.
Part of the VaultPDF family of privacy-first tools. Built early for the fast-growing, still-uncrowded MCP / agent-app ecosystem.
Tools
Free (no license needed):
| tool | what it does |
|---|---|
pdf_info | page count + per-page dimensions of a PDF |
pdf_merge | merge several PDFs into one, in order |
pdf_split | extract pages (e.g. 1-3,5,8) into a new PDF |
images_to_pdf | combine JPG/PNG images into a PDF, one per page |
Pro (one-time license — see below):
| tool | what it does |
|---|---|
pdf_watermark | stamp a diagonal text watermark on every page |
pdf_rotate | rotate all or selected pages by 90/180/270° |
pdf_delete_pages | remove selected pages (e.g. 2,5-7) |
All operations run locally via pdf-lib. Nothing leaves the machine.
Pro license — one-time, crypto, no subscription
The free tools work forever. To unlock the Pro tools:
- Send 9 USDC on Base to
0xe339997037C7e1C81829fA3e110d3e82B4bDd48E - Open an issue with your tx hash and email.
- A bot verifies the payment on-chain and replies with your license key (usually within minutes).
- Set it once and restart:
{ "mcpServers": { "vaultpdf": { "command": "npx", "args": ["github:AlexeySamosadov/vaultpdf-mcp"], "env": { "VAULTPDF_LICENSE": "<your-key>" } } } }
The key is an offline ECDSA-signed token — it's verified locally, never phoned home. No account, no tracking.
Run
# from npm (after publish):
npx vaultpdf-mcp
# or straight from GitHub, no install:
npx github:AlexeySamosadov/vaultpdf-mcp
Use in Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"vaultpdf": { "command": "npx", "args": ["github:AlexeySamosadov/vaultpdf-mcp"] }
}
}
Then ask Claude: "merge /path/a.pdf and /path/b.pdf into /path/out.pdf".
Distribution (early = low competition)
- MCP Registry +
awesome-mcp-servers(PRs). - npm as
vaultpdf-mcp(sonpx vaultpdf-mcpworks) — needs an npm login. - ChatGPT App via the Apps SDK (wrap this MCP server behind a hosted endpoint) — needs an OpenAI developer account.
- Claude Skills directory entry. Same capability, listed everywhere — that's how agent tools get reach in 2026.
Why
PDF manipulation is one of the most common things people ask AI agents to do, and almost no MCP server does it locally / privately. Free + open to drive adoption; funnels to the paid VaultPDF web tools and a future hosted Pro tier.
MIT licensed.