Nutrient Document Processing

Note: This skill integrates with the Nutrient commercial API. Review their terms before use.

Process documents with the Nutrient DWS Processor API. Convert formats, extract text and tables, OCR scanned documents, redact PII, add watermarks, digitally sign, and fill PDF forms.

Setup

Get a free API key at nutrient.io

bash
1export NUTRIENT_API_KEY="pdf_live_..."

All requests go to https://api.nutrient.io/build as multipart POST with an instructions JSON field.

Operations

Convert Documents

bash
1# DOCX to PDF
2curl -X POST https://api.nutrient.io/build \
3  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
4  -F "document.docx=@document.docx" \
5  -F 'instructions={"parts":[{"file":"document.docx"}]}' \
6  -o output.pdf
7
8# PDF to DOCX
9curl -X POST https://api.nutrient.io/build \
10  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
11  -F "document.pdf=@document.pdf" \
12  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"docx"}}' \
13  -o output.docx
14
15# HTML to PDF
16curl -X POST https://api.nutrient.io/build \
17  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
18  -F "index.html=@index.html" \
19  -F 'instructions={"parts":[{"html":"index.html"}]}' \
20  -o output.pdf

Supported inputs: PDF, DOCX, XLSX, PPTX, DOC, XLS, PPT, PPS, PPSX, ODT, RTF, HTML, JPG, PNG, TIFF, HEIC, GIF, WebP, SVG, TGA, EPS.

Extract Text and Data

bash
1# Extract plain text
2curl -X POST https://api.nutrient.io/build \
3  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
4  -F "document.pdf=@document.pdf" \
5  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"text"}}' \
6  -o output.txt
7
8# Extract tables as Excel
9curl -X POST https://api.nutrient.io/build \
10  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
11  -F "document.pdf=@document.pdf" \
12  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"xlsx"}}' \
13  -o tables.xlsx

OCR Scanned Documents

bash
1# OCR to searchable PDF (supports 100+ languages)
2curl -X POST https://api.nutrient.io/build \
3  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
4  -F "scanned.pdf=@scanned.pdf" \
5  -F 'instructions={"parts":[{"file":"scanned.pdf"}],"actions":[{"type":"ocr","language":"english"}]}' \
6  -o searchable.pdf

Languages: Supports 100+ languages via ISO 639-2 codes (e.g., eng, deu, fra, spa, jpn, kor, chi_sim, chi_tra, ara, hin, rus). Full language names like english or german also work. See the complete OCR language table for all supported codes.

Redact Sensitive Information

bash
1# Pattern-based (SSN, email)
2curl -X POST https://api.nutrient.io/build \
3  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
4  -F "document.pdf=@document.pdf" \
5  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"social-security-number"}},{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"email-address"}}]}' \
6  -o redacted.pdf
7
8# Regex-based
9curl -X POST https://api.nutrient.io/build \
10  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
11  -F "document.pdf=@document.pdf" \
12  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"regex","strategyOptions":{"regex":"\\b[A-Z]{2}\\d{6}\\b"}}]}' \
13  -o redacted.pdf

Presets: social-security-number, email-address, credit-card-number, international-phone-number, north-american-phone-number, date, time, url, ipv4, ipv6, mac-address, us-zip-code, vin.

Add Watermarks

bash
1curl -X POST https://api.nutrient.io/build \
2  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
3  -F "document.pdf=@document.pdf" \
4  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"watermark","text":"CONFIDENTIAL","fontSize":72,"opacity":0.3,"rotation":-45}]}' \
5  -o watermarked.pdf

Digital Signatures

bash
1# Self-signed CMS signature
2curl -X POST https://api.nutrient.io/build \
3  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
4  -F "document.pdf=@document.pdf" \
5  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"sign","signatureType":"cms"}]}' \
6  -o signed.pdf

Fill PDF Forms

bash
1curl -X POST https://api.nutrient.io/build \
2  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
3  -F "form.pdf=@form.pdf" \
4  -F 'instructions={"parts":[{"file":"form.pdf"}],"actions":[{"type":"fillForm","formFields":{"name":"Jane Smith","email":"jane@example.com","date":"2026-02-06"}}]}' \
5  -o filled.pdf

MCP Server (Alternative)

For native tool integration, use the MCP server instead of curl:

json
1{
2  "mcpServers": {
3    "nutrient-dws": {
4      "command": "npx",
5      "args": ["-y", "@nutrient-sdk/dws-mcp-server"],
6      "env": {
7        "NUTRIENT_DWS_API_KEY": "YOUR_API_KEY",
8        "SANDBOX_PATH": "/path/to/working/directory"
9      }
10    }
11  }
12}

When to Use

• Converting documents between formats (PDF, DOCX, XLSX, PPTX, HTML, images)
• Extracting text, tables, or key-value pairs from PDFs
• OCR on scanned documents or images
• Redacting PII before sharing documents
• Adding watermarks to drafts or confidential documents
• Digitally signing contracts or agreements
• Filling PDF forms programmatically

Links

• API Playground
• Full API Docs
• npm MCP Server