Enterprise-Grade PII Detection & Anonymization
Regex patterns for structured data, proven ML models for names. Transparent, auditable results on Hetzner's ISO 27001-certified servers in Germany.
Why Choose anonym.legal
Deterministic Pattern Detection
Regex patterns for structured data (emails, SSNs, credit cards) give 100% reproducible results. ML-based NER for names and organizations provides high consistency. Fully auditable for compliance.
Learn about our technology →Hetzner Germany, ISO 27001 Certified
All processing happens in Hetzner's ISO 27001-certified data centers in Germany. Your data stays in the EU with no surprise jurisdiction issues.
View security details →Token-Based Pricing You Can Understand
Pay for what you use with our transparent token system. Free tier includes 200 tokens (~15-18 pages/month). No hidden fees, no surprises.
See pricing →AI Integration with Privacy Protection
Connect your AI tools like Cursor and Claude Desktop while keeping your sensitive data safe with automatic PII anonymization.
Your AI Tool
(Cursor, Claude)
MCP Server
(Anonymizes PII)
AI Processes
(Safe data only)
Restore Values
(Optional)
The MCP Server acts as a privacy shield between your AI tools and sensitive data. It automatically detects and anonymizes PII before sending to AI, then restores original values in responses—ensuring AI never sees your real data.
Seamless AI Tool Integration
Works with Cursor, Claude Desktop, and other MCP-compatible tools
Privacy-First Architecture
AI processes anonymized data only—original PII never leaves your control
Reversible Anonymization
Tokenization allows you to restore original values when needed
Same Token Pricing
Uses your existing token balance—no additional cost
Supported AI Tools:
Available on Pro and Business plans. Upgrade to unlock.
Process Documents Securely
Maximum privacy with secure file handling. Documents stay on your device — only extracted text is sent for analysis.
Drag & Drop
(Your files)
Local Processing
(On your device)
Analyze & Anonymize
(Text only)
Save Result
(Stay local)
The Desktop App processes documents entirely on your device. Files are read locally, only the extracted text is sent for analysis, and your documents stay private.
Secure File Handling
Documents stay on your computer — only extracted text is sent to our secure API
Encrypted Local Storage
History, presets, and encryption keys stored in your encrypted local vault
Drag & Drop Interface
Simple, intuitive workflow—drag files and get results instantly
Multiple Formats
PDF, DOCX, TXT, and more—process any document type
Available for:
Detect names, emails, phone numbers, credit cards, SSNs, IBANs, IP addresses, and more across multiple categories.
Full support for 48 languages including English, German, Spanish, French, and 43 more with RTL support for Arabic, Hebrew, Persian, and Urdu. Powered by spaCy, Stanza, and XLM-RoBERTa NLP engines.
Replace, Redact, Hash (SHA-256), Encrypt (AES-256-GCM), or Mask—choose the protection method that fits your use case.
Enterprise-grade reliability with monitoring, automated backups, and incident response procedures.
Free Compliance & Security Guides
Download expert resources to help your organization protect sensitive data and meet compliance requirements.
See It in Action
Watch how anonym.legal protects sensitive data in real-time across your favorite tools.

Latest Insights
Research, guides, and analysis on data privacy
Japan My Number: Verhoeff & APPI
63% of generic tools fail My Number detection in Japanese documents. My Number uses Verhoeff algorithm — the most complex national ID checksum in Asia.
HDPA Greece: AFM & AMKA Detection
Greek AFM detected with 52% accuracy by generic tools. HDPA issued 89 decisions in 2024 — up 162% from 2022. Tourism and maritime sectors face distinct.
NAIH Hungary: TAJ-Szám and Adóazonosító Jel
Hungarian NER accuracy is 67% vs. EU average 82% — NAIH's 2024 assessment. TAJ-szám weighted checksum and adóazonosító jel detection gaps.
Ready to Protect Your Data?
Start with our free tier—200 tokens per cycle, no credit card required.