Documentation

MCP Server, REST API, and SDK integration guides for anonym.legal and cloak.business

MCP Server

7 tools via NPM · Claude Desktop, Cursor, VS Code

REST API

Direct API integration · no SDK required

Code Examples

Python, JavaScript, cURL

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "anonymize": {
      "command": "npx",
      "args": ["-y", "@anthropic-ai/mcp-server-anonym-legal"],
      "env": { "ANONYM_LEGAL_API_KEY": "your-api-key" }
    }
  }
}

Config locations:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Cursor IDE

Add to Cursor MCP settings (Settings › Features › MCP):

{
  "mcpServers": {
    "anonymize": {
      "command": "npx",
      "args": ["-y", "@anthropic-ai/mcp-server-anonym-legal"],
      "env": { "ANONYM_LEGAL_API_KEY": "your-api-key" }
    }
  }
}

7 MCP Tools

Tool	Description
`anonymize_text`	Anonymize text — replace, redact, hash, encrypt, mask, or keep per entity
`analyze_text`	Detect PII entities — returns positions, types, and confidence scores
`detokenize_text`	Restore original values from session tokens
`get_balance`	Check remaining token balance
`estimate_cost`	Estimate token cost before calling anonymize_text
`list_sessions`	List active anonymization sessions
`delete_session`	Delete a session — GDPR Art. 17 erasure

Environment Variables

Variable	Required	Description
`ANONYM_LEGAL_API_KEY`	Yes	API key from anonym.legal
`ANONYM_METHOD`	No	Default: replace. Options: replace, redact, hash, encrypt, mask, keep
`ANONYM_LANGUAGE`	No	Default: auto. ISO 639-1 language code

Base URL

https://api.anonym.legal/v1

Authentication

Include your API key in the Authorization header:

Authorization: Bearer your-api-key

POST/anonymize

Anonymize text and detect PII entities.

Request Body

{
  "text": "John Smith's email is john@example.com",
  "method": "replace",
  "language": "en",
  "entities": ["PERSON", "EMAIL_ADDRESS"]
}

Response

{
  "anonymized": "Max Mueller's email is max.mueller@example.de",
  "entities": [{ "type": "PERSON", "original": "John Smith", "start": 0, "end": 10 }],
  "tokens_used": 2
}

POST/detokenize

Restore original values from session tokens.

{ "text": "enc_xK9mP2... email is enc_jL7nQ4...", "session_id": "abc123" }

Python (requests)

import requests

API_KEY = "your-api-key"
BASE_URL = "https://api.anonym.legal/v1"

def anonymize(text, method="replace"):
    response = requests.post(
        f"{BASE_URL}/anonymize",
        headers={"Authorization": f"Bearer {API_KEY}"},
        json={"text": text, "method": method}
    )
    return response.json()

result = anonymize("Contact John at john@example.com")
print(result["anonymized"])
# → "Contact Max Mueller at max.mueller@example.de"

JavaScript / Node.js

const BASE_URL = 'https://api.anonym.legal/v1';
const API_KEY  = 'your-api-key';

const result = await fetch(`${BASE_URL}/anonymize`, {
  method: 'POST',
  headers: { 'Authorization': `Bearer ${API_KEY}`, 'Content-Type': 'application/json' },
  body: JSON.stringify({ text: 'Contact John at john@example.com', method: 'replace' })
}).then(r => r.json());

console.log(result.anonymized);
// → "Contact Max Mueller at max.mueller@example.de"

cURL

curl -X POST https://api.anonym.legal/v1/anonymize \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"text":"Contact John at john@example.com","method":"replace"}'

MCP Server

10 tools · text, batch, image OCR

Python SDK

pip install cloak-business

Node.js SDK

npm i @cloak-business/sdk

Code Examples

Batch, image OCR, SDK snippets

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "cloak": {
      "command": "npx",
      "args": ["-y", "cloak-business-mcp-server"],
      "env": { "CLOAK_API_KEY": "your-api-key" }
    }
  }
}

Config locations:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Cursor IDE

Add to Cursor MCP settings (Settings › Features › MCP):

{
  "mcpServers": {
    "cloak": {
      "command": "npx",
      "args": ["-y", "cloak-business-mcp-server"],
      "env": { "CLOAK_API_KEY": "your-api-key" }
    }
  }
}

10 Available Tools

Tool	Description
`cloak_analyze_text`	Detect PII in text (320+ types, 70+ countries)
`cloak_anonymize_text`	Anonymize text with 7 operators
`cloak_deanonymize_text`	Restore original values from session
`cloak_batch_analyze`	Analyze 1–100 texts in one API call
`cloak_analyze_image`	OCR + PII detection in images (38 languages)
`cloak_redact_image`	Visually redact PII regions in images
`cloak_create_session`	Create a persistent anonymization session
`cloak_get_session`	Retrieve session token mappings
`cloak_list_presets`	List available entity preset configurations
`cloak_apply_preset`	Anonymize using a saved preset

Environment Variables

Variable	Required	Description
`CLOAK_API_KEY`	Yes	API key from cloak.business
`CLOAK_METHOD`	No	Default: replace. Options: replace, redact, hash, encrypt, mask, keep, rsa
`CLOAK_LANGUAGE`	No	Default: auto. ISO 639-1 language code

Python SDK

Install via pip:

pip install cloak-business

from cloak_business import CloakBusiness

client = CloakBusiness(api_key="your-api-key")

# Anonymize a single text
result = client.anonymize("John Smith emailed john@example.com")
print(result["anonymized"])

# Batch: 1–100 texts per call
results = client.batch_anonymize([
    "Patient: Alice, DOB 1985-04-12",
    "Invoice to Bob Corp, VAT DE123456789",
])
for r in results: print(r["anonymized"])

Full API reference: cloak.business/docs

Node.js SDK

Install via npm:

npm install @cloak-business/sdk

import { CloakBusiness } from '@cloak-business/sdk';

const client = new CloakBusiness({ apiKey: 'your-api-key' });

// Anonymize a single text
const result = await client.anonymize('John Smith emailed john@example.com');
console.log(result.anonymized);

// Batch: 1–100 texts per call
const batch = await client.batchAnonymize([
  'Patient: Alice, DOB 1985-04-12',
  'Invoice to Bob Corp, VAT DE123456789',
]);
batch.forEach(r => console.log(r.anonymized));

Full API reference: cloak.business/docs

Batch Processing (Python)

from cloak_business import CloakBusiness

client = CloakBusiness(api_key="your-api-key")

# Anonymize up to 100 documents per call
documents = [
    "HR record: Jane Doe, jane@corp.com, +49-30-12345678",
    "Contract: Acme GmbH, HRB 123456, VAT DE987654321",
    # ... up to 100 texts
]

results = client.batch_anonymize(documents, method="replace")
for i, r in enumerate(results):
    print(f"[{i}] {r['anonymized']}")

# Tokens consumed by this batch
total_tokens = sum(r.get("tokens_used", 0) for r in results)
print(f"{total_tokens} tokens used")

Image OCR + Redaction (Python)

from cloak_business import CloakBusiness
import base64, pathlib

client = CloakBusiness(api_key="your-api-key")

# Read image and encode to base64
image_b64 = base64.b64encode(
    pathlib.Path("scanned_contract.png").read_bytes()
).decode()

# Detect PII in image (OCR — 38 languages)
analysis = client.analyze_image(image_b64, language="de")
print("Found:", [e["type"] for e in analysis["entities"]])

# Redact visually — returns a new base64-encoded image
redacted = client.redact_image(image_b64, language="de")
pathlib.Path("redacted.png").write_bytes(base64.b64decode(redacted["image"]))

Round-trip Deanonymization (Node.js)

import { CloakBusiness } from '@cloak-business/sdk';
const client = new CloakBusiness({ apiKey: 'your-api-key' });

// Step 1: anonymize and save the session
const { anonymized, session_id } = await client.anonymize(
  'Call Alice at +49-30-555-1234 to discuss the contract.',
  { method: 'replace', createSession: true }
);
// → "Call Emma at +49-30-555-9876 to discuss the contract."

// Step 2: send anonymized text to AI model ...
const aiResponse = 'Follow up with Emma tomorrow.';

// Step 3: restore original values in AI response
const { deanonymized } = await client.deanonymize(aiResponse, { session_id });
console.log(deanonymized);
// → "Follow up with Alice tomorrow."

replace Default

Replaces PII with realistic fake data. Maintains document readability.

"John Smith" → "Max Mueller"

redact

Completely removes PII. Irreversible but maximum privacy.

"john@example.com" → "[REDACTED]"

hash SHA-256

One-way cryptographic hash. Consistent pseudonymization.

"555-0123" → "a7f3c9d2..."

encrypt AES-256-GCM

Military-grade encryption. Fully reversible with the correct key.

"DE89370400..." → "enc_xK9mP2..."

mask

Partial visibility with masked characters. Shows structure.

"4532-1234-5678-9012" → "4532-****-****-9012"

Need help?

Our team is ready to help you integrate Anonymize.dev into your workflow.

Contact Support Get API Key

Documentation

MCP Server

REST API

Code Examples

MCP Server Setup

Claude Desktop

Cursor IDE

7 MCP Tools

Environment Variables

REST API

Base URL

Authentication

POST/anonymize

Request Body

Response

POST/detokenize

Code Examples

Python (requests)

JavaScript / Node.js

cURL

MCP Server

Python SDK

Node.js SDK

Code Examples

MCP Server Setup

Claude Desktop

Cursor IDE

10 Available Tools

Environment Variables

SDK Reference

Python SDK

Node.js SDK

Code Examples

Batch Processing (Python)

Image OCR + Redaction (Python)

Round-trip Deanonymization (Node.js)

Anonymization Methods

Need help?