文档智能处理服务

+--------------------------------------------------------------------------------+
|                                                                                |
|  __  __  ____ ____        ____                                _                |
| |  \/  |/ ___|  _ \      |  _ \  ___   ___ _   _ _ __ ___   | |_ ___          |
| | |\/| | |   | |_) |_____| | | |/ _ \ / __| | | | '_ ` _ \  | __/ _ \         |
| | |  | | |___|  __/_____| |_| | (_) | (__| |_| | | | | | | | ||  __/         |
| |_|  |_|\____|_|        |____/ \___/ \___|\__,_|_| |_| |_|  \__\___|         |
|                                                                                |
|      ____       _       _ _ _                       _                          |
|     |_ _|_ __  | |_ ___| | (_) __ _  ___ _ __   ___| |                         |
|      | || '_ \ | __/ _ \ | | |/ _` |/ _ \ '_ \ / __| |                         |
|      | || | | || ||  __/ | | | (_| |  __/ | | | (__| |                         |
|     |___|_| |_| \__\___|_|_|_|\__, |\___|_| |_|\___|_|                         |
|                                |___/                                           |
|                                                                                |
|              MCP SERVER  |  OCR  |  ANALYZE  |  ORGANIZE                       |
|                                                                                |
+--------------------------------------------------------------------------------+

# macOS (via Homebrew)
brew install tesseract tesseract-lang  # OCR engine with all languages
brew install poppler                    # PDF rendering tools (pdftoppm)

git clone https://github.com/AndreasDietzel/mcp-document-intelligence.git
cd mcp-document-intelligence
npm install
npm run build

{
  "mcpServers": {
    "document-intelligence": {
      "command": "node",
      "args": ["/path/to/mcp-document-intelligence/build/index.js"],
      "env": {
        "NODE_ENV": "production"
      }
    }
  }
}

{
  "mcpServers": {
    "document-intelligence": {
      "command": "node",
      "args": ["/path/to/mcp-document-intelligence/build/index.js"],
      "env": {
        "NODE_ENV": "production"
      }
    }
  }
}

{
  "mcpServers": {
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "/path/to/your/documents"
      ]
    },
    "document-intelligence": {
      "command": "node",
      "args": ["/path/to/mcp-document-intelligence/build/index.js"]
    }
  }
}

{
  "filePath": "/path/to/document.pdf"
}

{
  "originalFilename": "20240124_143045_scan.pdf",
  "suggestedFilename": "20240124_143045_RE-2024-1234_rechnung_telekom.pdf",
  "documentDate": "24.01.2024",
  "references": ["RE-2024-1234"],
  "keywords": ["rechnung", "telekom"],
  "scannerDatePreserved": true,
  "textLength": 2450,
  "preview": "Rechnung Nr. RE-2024-1234..."
}

{
  "folderPath": "/path/to/folder",
  "recursive": true,
  "fileTypes": ["invoice", "contract"],
  "keywords": ["telekom", "vodafone"]
}

{
  "folderPath": "/path/to/folder",
  "totalFiles": 15,
  "duplicateGroups": [
    {
      "hash": "abc123...",
      "count": 3,
      "files": ["doc1.pdf", "doc1_copy.pdf", "duplicate.pdf"]
    }
  ],
  "documents": [
    { 
      "originalPath": "...", 
      "suggestedFilename": "...", 
      "ocrQuality": "good",
      "confidence": 0.95,
      "metadata": {...} 
    }
  ]
}

{
  "documents": [ /* array from analyze_folder */ ]
}

{
  "sourcePath": "/path/to/source",
  "archivePath": "/path/to/archive",
  "dryRun": false,
  "createCategories": true,
  "stateFile": "/tmp/state.json"
}

{
  "total": 150,
  "processed": 147,
  "moved": 145,
  "categorized": {
    "01_Finanzen": 45,
    "03_Gesundheit": 12,
    "06_Reisen": 23,
    "99_Sonstiges": 65
  },
  "errors": [{"file": "...", "error": "..."}]
}

{
  "downloadsPath": "~/Downloads",
  "archiveBasePath": "/path/to/archive",
  "autoMove": false,
  "maxFiles": 50
}

{
  "scanned": 23,
  "suggestions": [
    {
      "from": "~/Downloads/Rechnung.pdf",
      "to": "/archive/Zwanziger/2025/01_Finanzen/2025-03-15_Rechnung_Telekom.pdf",
      "year": 2025,
      "category": "Finanzen"
    }
  ],
  "filed": [],
  "errors": []
}

{
  "folderPath": "/path/to/large/folder",
  "targetArchivePath": "/path/to/archive",
  "chunkSize": 50,
  "stateFilePath": "/tmp/batch-state.json"
}

{
  "chunkCompleted": true,
  "totalFiles": 500,
  "processedFiles": 50,
  "successCount": 48,
  "errorCount": 2,
  "percentComplete": 10,
  "nextChunkExists": true,
  "stateFilePath": "/tmp/batch-state.json"
}

{
  "structure": {
    "2024": {
      "Rechnungen": ["Telekom", "Vodafone"],
      "Vertraege": ["..."]
    }
  },
  "assignments": [
    {
      "originalPath": "/path/scan001.pdf",
      "targetFolder": "2024/Rechnungen/Telekom",
      "newFilename": "2024-01-24_RE-123_rechnung_telekom.pdf"
    }
  ]
}

{
  "baseFolder": "/path/to/organized",
  "mode": "move",
  "createBackup": true,
  "operations": [
    {
      "originalPath": "/path/scan001.pdf",
      "targetFolder": "2024/Rechnungen/Telekom",
      "newFilename": "2024-01-24_RE-123_rechnung_telekom.pdf"
    }
  ]
}

{
  "success": true,
  "mode": "move",
  "filesProcessed": 15,
  "filesFailed": 0,
  "foldersCreated": 5,
  "backupCreated": true,
  "backupPath": "/path/.backup_2024-01-24T10-30-00.json",
  "results": [...]
}

{
  "baseFolder": "/path/to/organized",
  "operations": [ /* same as batch_organize */ ]
}

{
  "preview": [
    {
      "action": "move",
      "from": "/path/scan001.pdf",
      "to": "/path/organized/2024/Rechnungen/Telekom/2024-01-24_RE-123.pdf",
      "status": "ok"
    }
  ],
  "warnings": [],
  "stats": {
    "totalFiles": 15,
    "foldersToCreate": ["2024/Rechnungen/Telekom"],
    "conflicts": 0,
    "missingFiles": 0
  },
  "safeToExecute": true
}

{
  "baseFolder": "/path/to/organized"
}

{
  "success": true,
  "restored": 15,
  "failed": 0,
  "backupFile": "/path/.backup_2024-01-24T10-30-00.json"
}

{
  "documents": [ /* array from analyze_folder */ ],
  "format": "csv"
}

Filename,Path,Date,References,Keywords,OCR Quality,Confidence,Type
scan001.pdf,/path/scan001.pdf,24.01.2024,RE-2024-1234,rechnung;telekom,good,0.95,invoice
...

analyze_document with filePath: "/path/to/scanned_invoice.pdf"

You: "Analyze all documents recursively in my 2026 folder, find duplicates"

AI (using analyze_folder with recursive=true):
   → Scanned 10 levels deep
   → Found 150 documents
   → Detected 12 duplicates (3 groups)
   → Extracted: dates, invoice numbers, companies
   → OCR quality: 95% confidence average

AI (using suggest_folder_structure):
   → Proposes: 2026/Rechnungen/Telekom, 2026/Vertraege/Vodafone, etc.
   → Shows: Complete list of file renames and target folders

AI (using preview_organization):
   → Preview: 150 files will be moved
   → Folders to create: 8
   → Conflicts: 0
   → Safe to execute: YES

AI: "I found 150 documents (12 duplicates). Should I organize them into 
     2026/Rechnungen, 2026/Vertraege with smart filenames?"

You: "Yes, but copy instead of moving"

AI (using batch_organize with mode="copy", createBackup=true):
   → Copies all files (originals preserved)
   → Creates folder structure
   → Backup created for undo
   → Processes everything automatically

AI: "Done! Organized 150 documents, created 8 folders, backup saved.
     15 files processed, 0 failed. Type 'undo' to revert."

You: "Export the metadata as CSV"

AI (using export_metadata with format="csv"):
   → Exports all document metadata
   → Includes: filename, date, references, keywords, OCR quality

AI: "CSV exported with all metadata for 150 documents."

mcp-document-intelligence/
├── src/
│   └── index.ts          # Main server implementation
├── build/                # Compiled output
├── package.json
├── tsconfig.json
└── README.md