Nutrient Document Engine

What it does

Exposes professional-grade document processing capabilities via the Nutrient Document Engine. It enables AI agents to extract text, render pages as images, apply redactions for sensitive data, split documents, and manage PDF form data through natural language commands.

Tools

• Content Access: Extract text from PDFs, search within documents, and render pages as images.
• Document Editing: Split large contracts into sections and add custom watermarks.
• Security: Automatically identify and redact SSNs, credit cards, and other sensitive patterns using regex.
• Annotations: Add and manage highlights, sticky notes, and stamps on documents.
• System: Retrieve document metadata and monitor engine health.

Installation

1. Start the engine: git clone https://github.com/PSPDFKit/nutrient-document-engine-mcp.git && cd nutrient-document-engine-mcp && docker-compose up -d
2. Add to claude_desktop_config.json:

{
  "mcpServers": {
    "nutrient-document-engine": {
      "command": "npx",
      "args": ["-y", "@nutrient-sdk/document-engine-mcp-server"],
      "env": {
        "DASHBOARD_USERNAME": "admin",
        "DASHBOARD_PASSWORD": "password",
        "DOCUMENT_ENGINE_BASE_URL": "http://localhost:5000",
        "DOCUMENT_ENGINE_API_AUTH_TOKEN": "secret"
      }
    }
  }
}

Supported hosts

• Claude Desktop
• LangGraph
• OpenAI APIs