The Hidden Risk in AI-Assisted Work
Every time you use ChatGPT, Claude, or Cursor, you might be sharing sensitive information. Most users don't realize their data is being sent to third-party AI providers.
- Customer names and emails
- Financial account numbers
- Medical records and patient IDs
- Trade secrets and proprietary data
How It Works: Automatic Protection
You Write Normally
With sensitive data
AI Tool
Cursor, Claude, etc.
AI Processes
Safe placeholders only
Restore Values
Original data back
The MCP Server acts as a privacy shield between your AI tools and sensitive data. AI never sees your real information.
What Gets Protected?
The system automatically detects and protects 320+ types of sensitive information across 70+ countries
People
John Doe, Jane Smith, Dr. Williams
Emails
john@example.com, info@company.org
Phones
+1-555-1234, (555) 123-4567
Credit Cards
4532-1234-5678-9010
Addresses
123 Main Street, New York, NY
Dates
January 15, 2026, 01/15/2026
Medical Info
Patient ID, prescription numbers
Financial IDs
IBANs, Tax IDs, VAT numbers
Digital Identifiers
IP addresses, MAC addresses, URLs
And 280+ More Types
License plates, passport numbers, etc.
Key Benefits
Native Claude Desktop Integration
Stdio transport for Claude Desktop - just add to your config. HTTP endpoint for Cursor, VS Code, and any MCP-compatible tool.
6 Anonymization Operators
Choose the right method: Replace, Redact, Hash (SHA-256/512), Encrypt (AES-256), Mask, or Keep. Apply different operators per entity type.
Entity Groups & Presets
Use predefined groups (UNIVERSAL, FINANCIAL, DACH, FRANCE, NORTH_AMERICA) or create personal presets for consistent anonymization across sessions.
48 Languages Supported
Detects PII in English, German, French, Spanish, Chinese, Japanese, Arabic, and 41 other languages. RTL support included.
Personal Encryption Keys
Load your own AES-128/192/256 keys for encrypt operator. Decrypt anytime with your key. Keys stored securely in your account.
Session Management
Tokenization mode with session IDs for reversible anonymization. List, manage, and delete sessions. 24h or 30-day persistence options.
Setup in 2 Minutes
Choose stdio for Claude Desktop or HTTP for other tools
Claude Desktop (Recommended):
- Install Node.js 18+ if not already installed
- Run: npx @anthropic-ai/mcp-server-cloak-business
- Add to claude_desktop_config.json with your API key
- Restart Claude Desktop - 7 privacy tools available!
HTTP (Cursor, VS Code, etc.):
- Get your API key from Settings → API Access
- Add MCP server URL: https://cloak.business/mcp
- Configure Authorization header with Bearer token
- No installation required - works instantly
MCP Server vs Manual Redaction
| Aspect | Manual Redaction | cloak.business MCP |
|---|---|---|
| Speed | Minutes per document | < 1 second |
| Accuracy | Human error-prone | 95%+ AI accuracy |
| Reversible | No - permanent | Yes - fully reversible |
| Maintenance | Constant vigilance | Automatic |
| Languages | One at a time | 48 simultaneously |
| Integration | Copy/paste workflow | Seamless in your tools |
| Cost | Staff time | From €0/month |
Frequently Asked Questions
Which integration should I use - stdio or HTTP?
For Claude Desktop, use stdio (npx command) for best performance. For Cursor, VS Code extensions, or custom apps, use HTTP (just add URL). Both support all 7 tools.
What operators are available?
6 operators: Replace (fake data), Redact (remove), Hash (SHA-256/512), Encrypt (AES-256 with your key), Mask (partial hide), and Keep (exclude from anonymization).
Can I use my own encryption keys?
Yes! Load personal AES keys (16/24/32 chars) from your account or enter them manually. Encrypt with your key, decrypt later with the same key. Keys never leave your control.
What are entity groups?
Predefined collections: UNIVERSAL (common PII), FINANCIAL (banking), DACH (German-speaking), FRANCE, NORTH_AMERICA, etc. Saves time configuring which entities to detect.
What's the difference between redact and tokenize modes?
Redact mode permanently removes PII. Tokenize mode replaces with reversible tokens and returns a session_id. Use detokenize_text with the session_id to restore original values.
How do sessions work?
Tokenization creates sessions (24h or 30-day persistence). Use list_sessions to see active sessions, delete_session to remove them. Sessions store the mapping between tokens and original values.