Nutrient DWS MCP Server

Created By
Nutrienta year ago
Create, Edit, Sign, Redact your documents using natural language
Overview

What is Nutrient DWS MCP Server?

Nutrient DWS MCP Server is an open source solution that allows you to process documents using natural language. By connecting Nutrient DWS MCP Server to your favorite MCP client (like Claude Desktop), you can:

  • Batch process documents using natural language. Just watch and wait… or make a coffee.
  • Avoid writing scripts or glue code to handle your document processing needs. Just ask in plain language.
  • Access document processing features that are often difficult to find or are buried inside expensive software.

Features overview

FeatureDescription
Document creationMerge PDFs, Office documents, and images
EditingWatermark, rotate, flatten, redact, and more
Format conversionPDF ⇄ DOCX, images, PDF/A support
Digital signingAdd PAdES standards-compliant digital signatures using trusted certificates
Data extractionExtract text, tables, or structured content
SecurityRedaction presets, password protection, permission control
Advanced OCRMulti-language image and scan recognition
OptimizationCompress files without quality loss

How to use Nutrient DWS MCP Server?

  1. Get a Nutrient DWS API key: Sign up at nutrient.io/api.
  2. Download Claude Desktop: If you haven’t already, download Claude Desktop and sign in.
  3. Install Node.js: Install Node.js with a package manager like brew on the command line. (brew install node)
  4. Configure Claude: Add your API key and set the directory you’d like to use as a sandbox in claude_desktop_config.json (~/Library/Application\ Support/Claude/claude_desktop_config.json on macOS).
{
	"mcpServers": {
		"nutrient-dws": {
			"command": "npx",
			"args": [
				"-y",
				"@nutrient-sdk/dws-mcp-server",
				"--sandbox",
				"</your/sandbox/directory>"
			],
			"env": {
				"NUTRIENT_DWS_API_KEY": "<YOUR_API_KEY_HERE>"
			}
		}
	}
}
  1. Restart Claude Desktop.
  2. Add documents for processing: Use any file manager to copy the documents into the sandbox directory set in the claude_desktop_config.json file above.
  3. 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”).

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.

FAQ

Why file-system-based? Direct binary transfers from the client aren’t yet supported in MCP ([trust me I tried][mcp-question]), so clients such as Claude cannot send a file directly to an MCP server like Nutrient’s. We felt the sandbox is the next best option, and it enables the batch processing use case, which is a bonus!

Why open source? Flexibility and community contributions! Adapt it to your workflows, send PRs, and propose new features.

Server Config

{
  "mcpServers": {
    "nutrient-dws": {
      "command": "npx",
      "args": [
        "-y",
        "@nutrient-sdk/dws-mcp-server",
        "--sandbox",
        "</your/sandbox/directory>"
      ],
      "env": {
        "NUTRIENT_DWS_API_KEY": "<YOUR_API_KEY_HERE>"
      }
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Nutrient
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago