Nutrient Document Engine
Exposes robust document processing capabilities through natural language interactions, enabling both human users and AI agents to manipulate and extract information from documents.
About
The Nutrient Document Engine connects AI agents to advanced document processing functionalities, allowing users and AI models to interact with documents using natural language commands. This Model Context Protocol (MCP) server implementation streamlines complex document workflows, from extracting specific data like names and phone numbers, to redacting sensitive information such as social security numbers, and even restructuring documents by splitting them into sections. It integrates seamlessly with popular AI platforms like Claude Desktop and LangGraph, offering a versatile solution for automating and enhancing document-centric tasks.
Key Features
- Annotations: Add, read, and delete document annotations (highlights, notes, stamps).
- 1 GitHub stars
- Security: Create and apply redactions using preset patterns or custom regex.
- Document Editing: Split, watermark, duplicate documents, and fill PDF forms.
- Content Access: Extract text, search documents, render pages, extract form data and table structures.
- System: Document discovery, metadata retrieval, and health monitoring.
Use Cases
- Splitting large documents (e.g., 50-page contracts) into separate, manageable sections.
- Redacting sensitive information (e.g., social security numbers) from tax forms.
- Extracting specific data (e.g., names, phone numbers) from invoices or other documents.