AI & AGENTS

The document infrastructure AI agents need

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.

AI agents connected to Nutrient document infrastructure via MCP Server

THE READ-WRITE GAP

AI agents can read documents. They can't write them.

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

Read and understand

Summarize and extract text

Parse content, answer questions, and pull structured data from documents.


Classify and categorize

Identify document types, detect intent, and route to the right workflow.


Translate and compare

Convert between languages and surface semantic differences between versions.

WHAT LLMs CAN'T DO

Write and manipulate

Render, sign, and validate

Pixel-perfect PDF rendering, PAdES digital signatures, PDF/A compliance validation.


Fill forms and flatten

Populate interactive form fields, flatten annotations, apply watermarks.


Redact with precision

Permanent, irrecoverable PII removal — not black boxes layered on top of text.


THE DOCUMENT COMPANY

One platform, four pillars

Nutrient is the document company. From low-level SDKs to AI-powered workflows, we provide the full stack developers and enterprises need to build, integrate, automate, and understand documents at scale.

Build

SDKs and APIs for viewing, editing, annotating, signing, and converting documents across every platform — web, iOS, Android, Windows, macOS, Linux, and server.

Integrate

Platform integrations for SharePoint, Power Automate, and enterprise content management systems. Drop Nutrient into the tools your teams already use.

Automate

Workflow automation for operations teams. Drag-and-drop document processing, extraction, and routing — no code required.

Understand

AI and Vision API for intelligent document understanding. OCR, table extraction, key-value pairing, and content classification powered by hybrid AI models.

MCP Server: natural-language document operations

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.

User

Identified 47 PII entities across 3 files. Applied redactions, embedded PAdES signatures, converted to PDF/A-3. Files ready in ./sandbox.


Extract the invoice table, then merge all receipts into a single report.

User

Extracted 12 line items as JSON. Merged 8 receipts into consolidated-report.pdf (23 pages).


OCR this scanned document, fill the form fields from the extracted data, and flatten it.

User

OCR complete (English, 98.7% confidence). Populated 14 form fields. Flattened to read-only PDF.


GET STARTED IN MINUTES

Connect your agent to Nutrient

Add to your Claude Desktop config:

{ "mcpServers": { "nutrient-dws": { "command": "npx", "args": ["-y", "@nutrient-sdk/dws-mcp-server"], "env": { "NUTRIENT_DWS_API_KEY": "YOUR_KEY" } } } }


Restart Claude Desktop

The MCP server starts automatically. Drop documents into your sandbox directory.


Prompt in natural language:

"Convert all PDFs in ./inbox to DOCX, redact PII, and save to ./outbox."

WORKS WITH EVERY AGENT FRAMEWORK

Claude, GPT, LangGraph, and more

Claude Desktop / Anthropic tool use

Native MCP protocol support. Add the server to your claude_desktop_config.json and start prompting.


OpenAI Agents / GPT function calling

Expose the server's JSON schema as function tools. Deterministic responses, no hallucinated API calls.


LangGraph / LangChain

Wire Nutrient operations as tool nodes in your graph. Each operation returns structured JSON.


Custom agent frameworks

HTTP/SSE or stdio transport. JSON schema tool definitions work with any framework that supports tool use.



COMING SOON

Vision API: hybrid document intelligence

A new approach to document understanding that combines vision language models with traditional algorithmic OCR. Table extraction, key-value pairing, and intelligent character recognition — powered by a hybrid pipeline that delivers the accuracy of proven algorithms with the flexibility of modern AI. Purpose-built for the documents AI agents struggle with most: scanned forms, handwritten notes, and complex multi-column layouts.


AI Document Assistant

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.


  • In-document Q&A with source references
  • AI-powered redaction with human-in-the-loop
  • Summarize, translate, and classify on selection
Web, iOS, and Android SDKs

Embed AI Assistant into any app on any platform with a few lines of code.

Bring your own LLM

OpenAI, Anthropic, AWS Bedrock, or self-hosted open source models — your choice.

Semantic document comparison

AI-enhanced diffs that surface meaning-level changes, not just character differences.


TRUSTED AT SCALE

Infrastructure that enterprises depend on

Nutrient processes millions of documents daily for organizations that can't afford to get document handling wrong.

15%
of the Global 500 trust Nutrient for document infrastructure
130+
public sector organizations across 24 countries
80+
nations where Nutrient-powered documents are used
SOC 2
Type 2 audited with GDPR and CSA compliance

SECURITY AND DEPLOYMENT

Your infrastructure, your rules

Document compliance is infrastructure, not intelligence. Deploy Nutrient on your terms — self-hosted, managed cloud, or hybrid — with the security controls your organization requires.

Sandboxed execution

Every MCP job runs in an isolated workspace. Secrets and file systems stay safe.


Self-hosted or managed cloud

Deploy on your infrastructure with your LLM, or use Nutrient's managed cloud with dedicated SLAs.


Your data stays yours

Nutrient never trains models on your documents. Self-hosted LLMs keep everything within your perimeter.


Audit-ready by default

Every operation is logged and traceable. SOC 2 Type 2 audited, GDPR-compliant, and built for regulated industries.


REGULATED INDUSTRIES

Need isolated, compliance-ready document agents?

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.


Give your AI agents document superpowers

Free trial includes full MCP Server access, all SDK components, and Document Engine.


Frequently asked questions

What is Nutrient MCP Server and how does it work with AI agents?

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" — the MCP server handles the actual document operations. It supports HTTP/SSE and stdio transport, works with Claude, GPT, LangGraph, and any MCP-compatible agent framework.

What is the read-write gap and why does it matter?

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.

Why can't AI agents just process documents directly with an LLM?

LLMs are excellent at understanding and generating text, but they cannot perform deterministic document operations. They can't render a PDF page, cryptographically sign a document, validate PDF/A compliance, fill interactive form fields, or perform pixel-accurate redaction. These operations require purpose-built document infrastructure — which is exactly what Nutrient provides and what the MCP server exposes to your agents.

Which agent frameworks are supported?

Nutrient MCP Server works with any framework that supports tool use / function calling:

  • Claude Desktop and Anthropic API — Native MCP protocol support.
  • OpenAI Agents and GPT — Expose as function tools via JSON schema.
  • LangGraph and LangChain — Wire as tool nodes in your agent graph.
  • Custom frameworks — HTTP/SSE or stdio transport with standard JSON schema tool definitions.
What document operations can my agent perform?

The full Nutrient DWS feature set is available:

  • Conversion — PDF ⇄ DOCX, HTML, PNG, TIFF, and more.
  • AI redaction — Automatic PII, PHI, PCI detection and permanent removal.
  • Extraction — Tables, key-value pairs, and structured data as JSON.
  • Digital signatures — PAdES-compliant signing and certificate validation.
  • OCR — Multi-language optical character recognition.
  • Merge and split — Combine or split documents by page, bookmark, or content.
  • PDF/A and accessibility — Archival compliance and PDF/UA.
  • Forms — Read, fill, and flatten interactive form fields.
  • Watermarks and annotations — Branded overlays and markup.
What is the Vision API?

Vision API is an upcoming Nutrient product that combines vision language models (VLMs) with traditional algorithmic OCR to deliver hybrid document intelligence. It's designed for the documents AI agents struggle with most — scanned forms, handwritten notes, and complex layouts. Capabilities include table extraction, key-value pairing, and intelligent character recognition (ICR). Contact sales to learn more about early access.

How does Nutrient handle security for agent-driven document processing?

Security is built into the infrastructure:

  • Sandboxed execution — Every MCP job runs in an isolated workspace.
  • Stateless streaming — No documents persist between requests unless you explicitly save them.
  • Self-hosted option — Deploy on your infrastructure with your own LLM for complete data sovereignty.
  • SOC 2 Type 2 — Audited security controls for enterprise deployments.
  • No training on your data — Nutrient never uses your documents to train models.
Is the MCP Server open source?

Yes. The Nutrient DWS MCP Server is MIT-licensed and available on GitHub. Fork it, extend it, or contribute.

How do I get started?

Three steps:

  • Sign up for a free API key at dashboard.nutrient.io.
  • Add the MCP server to your Claude Desktop config: { "mcpServers": { "nutrient-dws": { "command": "npx", "args": ["-y", "@nutrient-sdk/dws-mcp-server"] } } }
  • Prompt: "Convert all PDFs in ./inbox to DOCX and redact PII."

For detailed guides, see the MCP Server page or developer documentation.