Nutrient Document Processing

export NUTRIENT_API_KEY="pdf_live_..."

# 从 DOCX 转换为 PDF
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.docx=@document.docx" \
  -F 'instructions={"parts":[{"file":"document.docx"}]}' \
  -o output.pdf

# 从 PDF 转换为 DOCX
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"docx"}}' \
  -o output.docx

# 从 HTML 转换为 PDF
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "index.html=@index.html" \
  -F 'instructions={"parts":[{"html":"index.html"}]}' \
  -o output.pdf

# 提取纯文本
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"text"}}' \
  -o output.txt

# 将表格提取为 Excel
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"output":{"type":"xlsx"}}' \
  -o tables.xlsx

# 对扫描件进行 OCR 并生成可搜索的 PDF（支持 100 多种语言）
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "scanned.pdf=@scanned.pdf" \
  -F 'instructions={"parts":[{"file":"scanned.pdf"}],"actions":[{"type":"ocr","language":"english"}]}' \
  -o searchable.pdf

# 基于模式（社会安全号码 SSN、电子邮件）
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"social-security-number"}},{"type":"redaction","strategy":"preset","strategyOptions":{"preset":"email-address"}}]}' \
  -o redacted.pdf

# 基于正则表达式
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"redaction","strategy":"regex","strategyOptions":{"regex":"\\b[A-Z]{2}\\d{6}\\b"}}]}' \
  -o redacted.pdf

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

# 自签名 CMS 签名
curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer $NUTRIENT_API_KEY" \
  -F "document.pdf=@document.pdf" \
  -F 'instructions={"parts":[{"file":"document.pdf"}],"actions":[{"type":"sign","signatureType":"cms"}]}' \
  -o signed.pdf

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

{
  "mcpServers": {
    "nutrient-dws": {
      "command": "npx",
      "args": ["-y", "@nutrient-sdk/dws-mcp-server"],
      "env": {
        "NUTRIENT_DWS_API_KEY": "YOUR_API_KEY",
        "SANDBOX_PATH": "/path/to/working/directory"
      }
    }
  }
}