AGENT INFRASTRUCTURE
AI agents can read and understand documents. They can’t render PDFs, apply digital signatures, validate compliance, or fill form fields. Nutrient provides the document infrastructure layer — deterministic, auditable, production-ready — so your agents can do real work with real documents.
THE READ-WRITE GAP
Large language models excel at understanding, summarizing, and extracting information from documents. But they cannot render a PDF page, cryptographically sign a contract, validate PDF/A compliance, fill interactive form fields, or perform pixel-accurate redaction. These operations require purpose-built document infrastructure — deterministic, auditable, and battle-tested. Nutrient bridges this gap.
WHAT LLMs CAN DO
Parse content, answer questions, and pull structured data from documents.
Identify document types, detect intent, and route to the right workflow.
Convert between languages and surface semantic differences between versions.
WHAT LLMs CAN’T DO
Pixel-perfect PDF rendering, PAdES digital signatures, PDF/A compliance validation.
Populate interactive form fields, flatten annotations, apply watermarks.
Permanent, irrecoverable PII removal — not black boxes layered on top of text.
Hand your LLM a prompt. Get a finished, compliant document back. No SDKs to learn, no API calls to write — just infrastructure that works.
Redact all PII from these three contracts, sign them, and convert to PDF/A-3.
Extract the invoice table. Then merge all receipts into a single report.
OCR this scanned document, fill the form fields from the extracted data, and flatten it.
GET STARTED IN MINUTES
.mcpb package from GitHub Releases and install it in Claude Desktop.
npx command shown here. Browser OAuth works there
too; add an API key only for CI or headless runs.
SANDBOX_PATH=/your/sandbox/directory \npx -y @nutrient-sdk/dws-mcp-server
# Optional for CI or headless environmentsNUTRIENT_DWS_API_KEY=YOUR_KEY \SANDBOX_PATH=/your/sandbox/directory \npx -y @nutrient-sdk/dws-mcp-serverWORKS WITH EVERY AGENT FRAMEWORK
Install the packaged Claude Desktop extension and start prompting. The same MCP tool layer also fits Anthropic-powered workflows in your own runtime.
Expose the server’s JSON schema as function tools. Deterministic responses, no hallucinated API calls.
Wire Nutrient operations as tool nodes in your graph. Each operation returns structured JSON.
Use stdio transport with standard JSON schema tool definitions in any framework that supports tool use.
Every operation available to LLMs via MCP — deterministic, auditable, and production-ready.
AVAILABLE NOW
Document understanding that combines vision language models with traditional algorithmic OCR. Table extraction, key-value pairing, and intelligent character recognition, delivered by a hybrid pipeline with the accuracy of proven algorithms and the flexibility of modern AI. Purpose-built for the documents AI agents struggle with most: scanned forms, handwritten notes, and complex multicolumn layouts. Shipping today in the Data Extraction API's understand and agentic modes, with per-field confidence and source grounding.
Embed an AI assistant directly inside your document viewer. Users ask questions, summarize, translate, redact, and extract — in context, on the document they’re looking at.
Embed AI Assistant into any app on any platform with a few lines of code.
OpenAI, Anthropic, AWS Bedrock, or self-hosted open source models — your choice.
AI-enhanced diffs that surface meaning-level changes, not just character differences.
TRUSTED AT SCALE
Nutrient processes millions of documents daily for organizations that can’t afford to get document handling wrong.
SECURITY AND DEPLOYMENT
Document compliance is infrastructure, not intelligence. Deploy Nutrient on your terms — self-hosted, managed cloud, or hybrid — with the security controls your organization requires.
Every MCP job runs in an isolated workspace. Secrets and file systems stay safe.
Deploy on your infrastructure with your LLM, or use Nutrient’s managed cloud with dedicated SLAs.
Nutrient never trains models on your documents. Self-hosted LLMs keep everything within your perimeter.
Every operation is logged and traceable. SOC 2 Type 2 audited, GDPR-compliant, and built for regulated industries.
REGULATED INDUSTRIES
For enterprises in healthcare, legal, finance, and government — dedicated document processing agents with full audit trails, HIPAA/SOC 2/GDPR compliance, and zero access to anything but documents.
Free trial includes full MCP Server access, all SDK components, and Document Engine.
Nutrient MCP Server is an open source microservice that translates natural language prompts from any LLM into deterministic API calls to Nutrient’s document processing infrastructure. Your agent says “redact PII and sign this PDF,” and the MCP server handles the actual document operations. It works with Claude, GPT, LangGraph, and any MCP-compatible agent framework.
The read-write gap is the fundamental limitation of AI agents when working with documents. LLMs excel at reading — understanding, summarizing, and extracting information from documents. But they cannot write — render PDFs, apply cryptographic signatures, validate compliance standards, fill interactive forms, or perform pixel-accurate redaction. These write operations require deterministic, purpose-built document infrastructure. Nutrient bridges this gap by providing the infrastructure layer that makes AI agents capable of complete document workflows.
Nutrient MCP Server works with any framework that supports tool use/function calling:
The full Nutrient DWS feature set is available:
Vision API is the hybrid engine that combines vision language models (VLMs) with traditional algorithmic OCR to deliver document intelligence for the documents AI agents struggle with most: scanned forms, handwritten notes, and complex layouts. Its capabilities ship today through the Data Extraction API's understand and agentic modes, including table extraction, key-value pairing, and intelligent character recognition (ICR), with per-field confidence scores. As a standalone product, Vision API is in early access; contact Sales to learn more.
Security is built into the infrastructure:
Yes. The Nutrient DWS MCP Server is MIT-licensed and available on GitHub. Fork it, extend it, or contribute.
Three steps:
.mcpb package from GitHub Releases and install it in Claude Desktop.SANDBOX_PATH=./sandbox npx -y @nutrient-sdk/dws-mcp-server. Browser OAuth handles sign-in automatically in interactive setups.For detailed guides, see the MCP Server page or developer documentation.