# document-scanner MCP server

> Scans PDFs, screenshots, and scanned documents to detect PII and credentials using text layers and OCR before they are sent to an LLM.

- Repository: https://github.com/GuardBee/guardbee-mcp
- Page: https://hostedmcp.org/servers/guardbee/document-scanner
- Transport: stdio
- Stars: 2
- License: MIT
- Latest version: 0.4.1

## Install

### Claude Code

```sh
claude mcp add document-scanner -- npx -y @guardbee/mcp-document-scanner
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "document-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-document-scanner"
      ]
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "document-scanner": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-document-scanner"
      ]
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"document-scanner","type":"stdio","command":"npx","args":["-y","@guardbee/mcp-document-scanner"]}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "document-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-document-scanner"
      ]
    }
  }
}
```

### Codex

```sh
codex mcp add document-scanner -- npx -y @guardbee/mcp-document-scanner
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.document-scanner]
command = "npx"
args = ["-y", "@guardbee/mcp-document-scanner"]
```

### Gemini CLI

```sh
gemini mcp add -s user document-scanner npx -- -y @guardbee/mcp-document-scanner
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "document-scanner": {
      "command": "npx",
      "args": [
        "-y",
        "@guardbee/mcp-document-scanner"
      ]
    }
  }
}
```

## Tools (3)

- `scan_document`
- `scan_base64`
- `list_detectors`

## FAQ

### What types of files can be scanned?

The scanner supports PDF, PNG, JPEG, GIF, WebP, BMP, TIFF, and text files.

### Does the scanner require OCR to work?

No, OCR is optional. Without it, the scanner reads the PDF text layer, but it will report pages or images it could not read.

### What kind of sensitive information can it detect?

It detects various personal data and credentials including IBAN, passport numbers, email addresses, phone numbers, and more.

### Are there any limitations on file size or length?

By default, the scanner is limited to 25 MB and 50 pages per document.
