Nutrient DWS MCP Server

Give AI agents the power to generate, read, extract, process, and sign documents.

Description

A Model Context Protocol (MCP) server that connects AI assistants to the Nutrient Document Web Service (DWS) Processor and Data Extraction APIs — enabling document creation, editing, conversion, digital signing, OCR, and redaction, plus structured data extraction (typed JSON with bounding boxes and confidence, or schema-guided field extraction with per-field citations) through natural language.

Features

• Local stdio MCP server for Claude Desktop and other MCP-compatible clients
• Browser-based OAuth on the first request that uses the Nutrient API, with optional API-key fallback for CI and headless environments
• Document conversion, OCR, redaction, watermarking, annotation flattening, and digital signing (Processor API)
• Data extraction (Data Extraction API): parse whole documents to Markdown or spatial JSON, then pull named fields into a JSON schema you define, with per-field citations. Four parse modes: text (1 credit/page, no OCR), structure (1.5), understand (9, the default), agentic (18, VLM)
• Sandbox-aware local file handling with explicit output paths
• Read-only account lookup for DWS credits and usage

What You Can Do

Once configured, you (or your AI agent) can process documents through natural language:

You: "Merge report-q1.pdf and report-q2.pdf into a single document" AI: "Done! I've merged both reports into combined-report.pdf (24 pages total)."

You: "Redact all social security numbers and email addresses from application.pdf" AI: "I found and redacted 5 SSNs and 3 email addresses. The redacted version is saved as application-redacted.pdf."

You: "Digitally sign this contract with a visible signature on page 3" AI: "I've applied a PAdES-compliant digital signature to contract.pdf. The signed document is saved as contract-signed.pdf."

You: "Convert this PDF to markdown" AI: "Here's the markdown content extracted from your document..."

You: "OCR this scanned document in German and extract the text" AI: "I've processed the scan with German OCR. Here's the extracted text..."

You: "Pull the vendor, invoice number, total, and due date out of invoice-0341.pdf, with citations" AI: "Here are the four fields as JSON. Each value cites the page and bounding box it came from..."

Installation

Install it from Claude Desktop Settings -> Extensions if you are using Claude Desktop. If you are developing locally, use the manual setup below.

The Claude Desktop MCPB extension defaults its sandbox directory to ~/Documents/Nutrient. You can change that directory in the extension settings. Clearing the field starts the server without sandbox restrictions, so file operations can use any path visible to your user account.

1. Create a Nutrient Account

Sign up for free at nutrient.io/api.

For local desktop use, the recommended path is to omit NUTRIENT_DWS_API_KEY and complete the browser sign-in flow on the first request that uses the Nutrient API. For CI, headless environments, or scripted setups, create an API key in the dashboard and set NUTRIENT_DWS_API_KEY.

2. Configure Your AI Client

Choose your platform and add the configuration:

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

{
  "mcpServers": {
    "nutrient-dws": {
      "command": "npx",
      "args": ["-y", "@nutrient-sdk/dws-mcp-server"],
      "env": {
        "SANDBOX_PATH": "/your/project/documents",
        // "C:\\your\\project\\documents" for Windows
        // Optional for CI or headless usage:
        // "NUTRIENT_DWS_API_KEY": "YOUR_API_KEY_HERE"
      },
    },
  },
}

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

{
  "servers": {
    "nutrient-dws": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@nutrient-sdk/dws-mcp-server"],
      "env": {
        "SANDBOX_PATH": "${workspaceFolder}",
        // Optional for CI or headless usage:
        // "NUTRIENT_DWS_API_KEY": "YOUR_API_KEY_HERE"
      },
    },
  },
}

SANDBOX_PATH=/your/path npx @nutrient-sdk/dws-mcp-server

# Optional for CI or headless usage:
NUTRIENT_DWS_API_KEY=your_key SANDBOX_PATH=/your/path npx @nutrient-sdk/dws-mcp-server

3. Restart Your AI Client

Restart the application to pick up the new MCP server configuration.

4. Start Processing Documents

Place documents in your sandbox directory and use explicit file names or paths in prompts. Explicit paths are safer and more reliable than vague file-browsing requests.

Available Tools

Prompts

• sign_and_watermark — Add a text watermark to a document, then digitally sign the watermarked PDF.
• extract_document_fields — Extract named fields into a JSON object, optionally retaining citations in a file.
• redact_pii — Detect and permanently redact personally identifiable information from a document.
• parse_for_rag — Parse a document as Markdown for retrieval-augmented generation and search indexing.
• office_to_pdfa — Convert an Office document to an archival PDF/A file.

Document Processor Capabilities