Nutrient DWS MCP Server

What is Nutrient DWS MCP Server about?

Enables AI assistants to perform a wide range of PDF and document manipulations—such as digital signing, OCR, merging, watermarking, redaction, and format conversion—by exposing the Nutrient Document Web Service (DWS) Processor API through a Model Context Protocol (MCP) server.

How to use Nutrient DWS MCP Server?

1. Obtain an API key from the Nutrient dashboard.
2. Install Node.js (brew install node on macOS or download the installer for Windows).
3. Add a server entry to claude_desktop_config.json (or any MCP client configuration) using the provided npx command and environment variables (NUTRIENT_DWS_API_KEY and optional SANDBOX_PATH).
4. Start the server with npx -y @nutrient-sdk/dws-mcp-server.
5. Place input files in the sandbox directory (if sandbox mode is enabled).
6. Interact via the AI assistant, issuing natural‑language commands like “redact all PII from secret.pdf” or “merge contract.pdf and invoice.pdf”.

Key Features

• Document creation: merge PDFs, Office docs, and images.
• Editing tools: watermark, rotate, flatten, redact, etc.
• Format conversion: PDF ⇄ DOCX, image formats, PDF/A.
• Digital signing: PAdES‑compliant signatures with trusted certificates.
• Data extraction: text, tables, structured content.
• Security controls: redaction presets, password protection, permission management.
• Advanced OCR: multi‑language, scan and image recognition.
• Optimization: lossless compression.

Use Cases

• Legal workflows – automatically redact sensitive information and apply qualified digital signatures.
• Business automation – generate contracts from templates, merge multiple PDFs, and convert reports to DOCX.
• Data extraction – pull tables or structured data from invoices for downstream processing.
• Content preparation – add watermarks, rotate pages, or compress files before sharing.
• Secure archiving – enforce password protection and permission settings on confidential documents.

FAQ

Q: Do I have to use Claude Desktop? A: Claude Desktop is the reference client, but any MCP‑compatible client can connect to the server.

Q: Is sandbox mode required? A: It is strongly recommended for security. When SANDBOX_PATH is set, the server restricts all file operations to that directory.

Q: Which operating systems are supported? A: macOS and Windows are officially supported. Linux support may be added via community contributions.

Q: How do I specify the output location? A: In sandbox mode, instruct the assistant with a natural‑language path (e.g., “output to output/final.pdf”). The server will resolve it inside the sandbox.

Q: What environment variables are needed? A: NUTRIENT_DWS_API_KEY (mandatory) and optionally SANDBOX_PATH.

Nutrient DWS MCP Server

A Model Context Protocol (MCP) server implementation that integrates with the Nutrient Document Web Service (DWS) Processor API, providing powerful PDF processing capabilities for AI assistants.

This server allows AI assistants to access the tools provided by Nutrient DWS Processor API, enabling operations such as digital signing, document generation, document editing, OCR, watermarking, redaction, and more.

Table of Contents

• Features Overview
• Usage
  • Getting Started with Claude Desktop
  • Compatibility
  • Further Configuration
• Contributions

Features overview

Feature	Description
Document Creation	Merge PDFs, Office docs, and images
Editing	Watermark, rotate, flatten, redact, and more
Format Conversion	PDF ⇄ DOCX, images, PDF/A support
Digital Signing	Add PAdES standards-compliant digital signatures using trusted certificates
Data Extraction	Extract text, tables, or structured content
Security	Redaction presets, password protection, permission control
Advanced OCR	Multi-language, image and scan recognition
Optimization	Compress files without quality loss

Usage

Getting Started with Claude Desktop + Nutrient DWS MCP Server

1. Get a Nutrient DWS API key: Sign up at nutrient.io/api.
2. Install Node.js:
   1. macOS users: Install Node.js with a package manager like brew on the command line. (brew install node)
   2. Windows users: Download the Node Installer by visiting Node.js Download Site and run the installer
3. Download Claude Desktop: If you haven’t already, download Claude Desktop and sign in.
4. Create the claude_desktop_config.json:
   1. macOS users: Click on "Claude" next to the Apple icon on top of your mac screen. Go to Settings > Developer and click on Edit Config.
   2. Windows user: Click on the hamburger menu on the top left of the Claude Desktop window. Go to File > Settings > Developer and click on Edit Config.
5. Configure Claude:: Add nutrient-dws to the claude_desktop_config.json (example below). Make sure to add your API key and set the sandbox directory:
   1. macOS users: The claude_desktop_config.json is inside the directory ~/Library/Application\ Support/Claude.
   2. Windows users: The claude_desktop_config.json is inside the directory %APPDATA%\Claude

NOTE: For the SANDBOX_PATH, you can put in the path in either the Unix-style (separated using forward slash /) or the Windows-style (separated using the backward slash /). And for the Windows path, you must escape the backward slash (i.e. \\ instead of \)

{
  "mcpServers": {
    "nutrient-dws": {
      "command": "npx",
      "args": ["-y", "@nutrient-sdk/dws-mcp-server"],
      "env": {
        "NUTRIENT_DWS_API_KEY": "YOUR_API_KEY_HERE",
        "SANDBOX_PATH": "/your/sandbox/directory" // "C:\\your\\sandbox\\directory" for Windows
      }
    }
  }
}

6. Restart Claude Desktop.

   On Windows you might need to go to the Task Manager and kill any processes named Claude to reset the application. On a macOS it will be the Activity Monitor

7. Add documents for processing: Use any file manager to copy the documents into the sandbox directory set via the SANDBOX_PATH environment variable above.
8. Process documents: Instruct Claude Sonnet 3.7 (e.g. “redact all PII from secret.pdf”, “sign the document contract.pdf”, “merge secret.pdf and contract.pdf together”, etc.).

Note: All operations involve reading from and writing to files on disk. We strongly recommend using the sandboxed directory feature to enhance security and prevent data loss.

Compatibility

Nutrient DWS MCP Server has been tested with Claude Desktop (Claude 3.7 Sonnet). Other MCP clients may work, but results may vary.

Nutrient DWS MCP Server supports macOS and Windows for now. Feel free to open an issue if you’re interested in Linux support.

Further configuration

Sandbox mode (Recommended)

The server supports an optional sandbox mode that restricts file operations to a specific directory. This is useful for security purposes, ensuring that the server can only read from and write to files within the specified directory. You should drop any documents you'd like to work on in this directory.

To enable sandbox mode, set the SANDBOX_PATH environment variable:

export SANDBOX_PATH=/path/to/sandbox/directory
npx @nutrient-sdk/dws-mcp-server

When sandbox mode is enabled:

• For relative paths, they are resolved relative to the sandbox directory.
• All input file paths are validated to ensure they exist and reside in the sandbox before performing any file operations

If no sandbox directory is specified, the server will operate without file path restrictions, allowing access to any file on the system that the server process has permission to access. (Not Recommended)

Output location

Processed files will be saved to a location determined by the LLM. If sandbox mode is enabled, it will reside inside this directory.

To further guide the LLM on where to place the output file, use natural language such as "please output the result to output/my_result.pdf". Or you may also add an output directory in your sandbox to hint to the LLM to use this directory for all resulting files.

Contributions

Please see the contribution guidelines in CONTRIBUTING.md