# VaultPDF MCP 🔒

**Local PDF tools for AI agents.** An [MCP](https://modelcontextprotocol.io) 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](https://alexeysamosadov.github.io/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:

1. Send **9 USDC on Base** to `0xe339997037C7e1C81829fA3e110d3e82B4bDd48E`
2. [Open an issue](https://github.com/AlexeySamosadov/vaultpdf-mcp/issues/new) with your **tx hash** and **email**.
3. A bot verifies the payment on-chain and replies with your **license key** (usually within minutes).
4. Set it once and restart:
   ```json
   {
     "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
```bash
# 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`:
```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` (so `npx vaultpdf-mcp` works) — 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.