PSPDFKit (Now Nutrient)

Overview

Founded in 2011 by Peter Steinberger, PSPDFKit built its reputation on high-fidelity PDF rendering, annotation, and editing SDKs across iOS, Android, and JavaScript platforms. Following a €100M investment from Insight Partners in 2021, the company expanded through acquisitions of Muhimbi, ORPALIS, Aquaforest, and Integrify. In 2024, those products were unified under the Nutrient brand, marking the company's evolution from a PDF SDK into a broader document processing platform.

By early 2026, Nutrient had repositioned further — publishing three open-source Model Context Protocol servers and a production-ready Python SDK, signaling a deliberate push to become document processing infrastructure for agentic AI stacks rather than a standalone PDF tool.

How PSPDFKit (Now Nutrient) Processes Documents

PSPDFKit's core processing architecture separates rendering and SDK capabilities from server-side document transformation. The Document Engine handles splitting, merging, watermarking, form filling, redaction, and annotation at the server layer, while client SDKs (iOS, Android, JavaScript) handle viewing, annotation, and editing at the application layer.

In early 2026, Nutrient extended this architecture with three distinct MCP servers that expose document processing capabilities to AI agents via natural language:

Document Engine MCP Server (@nutrient-sdk/document-engine-mcp-server) targets self-hosted deployments. It wraps the Document Engine and exposes four capability areas to AI agents: content access (text extraction, page rendering, form and table extraction), document editing (splitting, watermarking, form filling), security and redaction (SSN and credit card presets plus custom regex), and annotations (highlights, notes, stamps). The server runs via npx, connects to a Document Engine instance on localhost:5000, and ships with four reference workflow implementations — a LangGraph contract processing pipeline, OpenAI Agents SDK equivalents, a React + LangGraph document chat interface, and a LangGraph.js procurement agent that classifies purchase orders, invoices, and payment documents and flags items for human review. The Document Engine requires a commercial ACTIVATION_KEY; evaluation mode adds watermarks.

DWS MCP Server (@nutrient-sdk/dws-mcp-server) connects AI agents to Nutrient's cloud Document Web Services Processor API via stdio transport, requiring only Node.js 18+ and a NUTRIENT_DWS_API_KEY. Four tools are exposed: document_processor (merge, convert, OCR, watermark, rotate, redact, flatten, extract text/tables/key-value pairs), document_signer (PAdES-compliant CMS and CAdES digital signatures, visible or invisible), sandbox_file_tree, and directory_tree. Format support spans PDF, DOCX, XLSX, PPTX, PNG, JPEG, WebP, PDF/A, PDF/UA, HTML, and Markdown. Supported platforms include Claude Desktop, Cursor, Windsurf, VS Code with GitHub Copilot, LangChain, LangGraph, and the OpenAI Agents SDK. A free tier is available at dashboard.nutrient.io; a sandbox mode restricts file operations to a specified directory.

PDF MCP Server (nutrient-pdf-mcp-server, PyPI: nutrient_pdf_mcp-1.0.0) is explicitly positioned as a developer debugging tool, not a production workflow server. It exposes two tools: get_pdf_object_tree (returns a JSON representation of the PDF object tree with lazy loading) and resolve_indirect_object (resolves a specific indirect object by object and generation number). Token efficiency is concrete: lazy mode returns 5–50 lines, shallow resolution 50–100 lines, and deep resolution 500+ lines. Navigation uses dot notation (e.g., Pages.Kids.0.MediaBox.2). Nutrient explicitly routes developers across all three servers by use case — this server for debugging, DWS MCP for cloud production workflows, Document Engine MCP for self-hosted production workflows.

The three-server architecture mirrors how mature developer platforms structure SDKs, separating concerns across debugging, cloud production, and self-hosted production rather than collapsing them into a single integration point.

Python SDK (launched February 2026) covers bidirectional document conversion (PDF, Word, Excel, PowerPoint, HTML, Markdown, images), OCR across 100+ languages with automated skew correction and noise removal, zone-based permanent redaction (claimed GDPR and HIPAA compliant, removing content from file structure rather than applying a visual overlay), key-value pair extraction for invoices, receipts, bank statements, and forms exported to JSON, digital signatures, fillable form creation and batch-fill from databases, and Word template population via JSON. The SDK includes type hints, async support, and compatibility with Django, Flask, and FastAPI. Batch processing scales linearly with CPU cores. Two capabilities are explicitly on the roadmap but not yet available: page-aware architecture enabling true concurrent processing of individual page objects, and AI-powered document understanding returning full document structure as JSON including relationships and hierarchies. A free trial is available at nutrient.io/sdk/try/.

The SDK's stated rationale — format preservation failures, library fragmentation, batch scaling limitations — frames competitors like PyMuPDF and pdfplumber as the baseline, positioning it as a consolidation play for Python developers currently stitching together multiple libraries rather than a direct enterprise IDP platform pitch.

Use Cases

Legal and Contracts

PDF annotation, redaction, and form filling SDKs are embedded in legal document review workflows. The Document Engine MCP Server ships with a LangGraph contract processing reference implementation, enabling AI agents to extract, classify, and route contract documents autonomously.

Financial Services

Key-value pair extraction via the Python SDK targets invoices, receipts, bank statements, and forms, exporting results to JSON. The DWS MCP Server exposes the same extraction capabilities to AI agents via cloud API. Redaction presets cover SSN and credit card patterns out of the box, with custom regex for additional PII types.

Procurement and Supply Chain

The Document Engine MCP Server's LangGraph.js procurement agent reference implementation classifies purchase orders, invoices, and payment documents and flags items for human review — a concrete workflow template for procurement automation teams.

Developer Tooling and AI Infrastructure

The three-tier MCP architecture and Python SDK together position Nutrient as document processing infrastructure for agentic AI stacks. Developers building on Claude Desktop, LangGraph, OpenAI Agents SDK, Cursor, Windsurf, or VS Code with GitHub Copilot can connect to Nutrient's document engine without custom integration work.

Technical Specifications

Resources

• Nutrient vendor page — current product information
• Company Website (formerly pspdfkit.com)
• Document Engine MCP Server — self-hosted agentic document processing (MIT)
• DWS MCP Server — cloud API agentic document processing (MIT)
• PDF MCP Server — PDF object tree debugging (MIT, PyPI: nutrient_pdf_mcp)
• Python SDK announcement — GA release with OCR, redaction, conversion, and extraction
• Agentic Document Processing — how AI agents transform document workflows
• Document Processing with Python — Python library comparison and implementation guide
• Self-Hosted Document Processing — deployment architecture and security considerations

Sources

• 2026-02 [vendor: Python SDK announcement | nutrient.io] Nutrient Python SDK GA release covering OCR, redaction, conversion, digital signatures, and key-value extraction (https://www.nutrient.io/blog/introducing-nutrient-python-sdk/)
• 2026-02 [github: Document Engine MCP Server | github.com/PSPDFKit] MIT-licensed MCP server connecting Document Engine to AI agents via LangGraph, OpenAI Agents SDK, and React reference implementations (https://github.com/PSPDFKit/nutrient-document-engine-mcp-server)
• 2026-02 [github: DWS MCP Server | github.com/pspdfkit] MIT-licensed MCP server connecting AI agents to Nutrient cloud Document Web Services API via stdio transport (https://github.com/pspdfkit/nutrient-dws-mcp-server)
• 2026-02 [github: PDF MCP Server | github.com/PSPDFKit] MIT-licensed developer debugging MCP server exposing PDF object tree exploration via get_pdf_object_tree and resolve_indirect_object tools (https://github.com/PSPDFKit/nutrient-pdf-mcp-server)

Company Information

Vienna, Austria • Founded 2011

PSPDFKit rebranded to Nutrient in 2024 following a €100M Insight Partners investment in 2021 and acquisitions of Muhimbi, ORPALIS, Aquaforest, and Integrify. See the Nutrient vendor page for current company information.