anonym.legal — Enterprise-Grade PII Detection & Anonymization
Regex patterns for set data, proven ML models for names. Transparent, audit-fit results on Hetzner's ISO 27001-matched servers in Germany. 285+ item types, 48 languages with RTL support, MCP Server for AI tools.
Platform Overview
anonym.legal is a Zero-Knowledge PII finding and PII strip platform designed for legal professionals and privacy-conscious teams. Features native MCP Server link-up for AI tools (Claude Desktop, Cursor, VS Code via Continue and Cline) and advanced Zero-Knowledge sign-in where your password never leaves your device.
What Makes anonym.legal Unique
Zero-Knowledge Authentication
Your password never leaves your device. Built with Argon2id + XChaCha20-Poly1305 encoding and AES-256-GCM vault encoding. 24-word recovery phrase for account recovery.
MCP Server for AI Tools
Native link-up with Claude Desktop (stdio), Cursor, and VS Code via Continue and Cline extensions (HTTP). 6 operators: encode, hash, mask, redact, replace, keep. Item groups and presets (UNIVERSAL, FINANCIAL, DACH, FRANCE, NORTH_AMERICA).
48 Languages + RTL Support
Extended language support including Arabic, Hebrew, Persian, and Urdu with right-to-left rendering. Powered by spaCy, Stanza, and XLM-RoBERTa transformers.
Legal-Focused Design
Optimized for contract PII strip, e-scan, and FOIA audit fit. Audit trails and reproducible results for legal document live.
Privacy-First AI Workflow
The MCP Server acts as a privacy shield between your AI tools and touchy data.
- AI Tool Request — Claude Desktop, Cursor, or VS Code (via Continue/Cline) sends request containing touchy data.
- MCP Interception — MCP Server intercepts and analyzes content for PII.
- PII Tokens — Touchy data replaced with tokens (e.g., PII_PERSON_001, PII_EMAIL_001)
- AI Processing — AI processes only anonymized info.
- Response Return — Response flows back through MCP Server.
- Optional De-tokens — First values can be restored if needed.
Multi-Engine Language Processing
anonym.legal uses three NLP engines optimized for other language families with lazy-loaded models for efficiency. Regex patterns for set data, ML models for names and teams.
spaCy Engine
25 Languages
Fast industrial-strength NLP for European languages and major world languages.
Stanza Engine
7 Languages
Stanford NLP engine for focused language processing and academic accuracy.
XLM-RoBERTa Transformer
16 Languages
Cross-lingual transformer for low-resource languages and multilingual docs.
PII Detection & Anonymization
285+ Entity Types
Names, emails, phone numbers, credit cards, SSNs, IBANs, IP addresses, and more. Pattern-based finding for set data, ML-based NER for names and teams. Confidence scoring for all detections.
5 Anonymization Methods
- Replace — Substitute with fake data.
- Redact — Full removal.
- Hash — SHA-256 hashing.
- Encrypt — AES-256-GCM encoding.
- Mask — Partial obscuring.
RTL Language Support
Full right-to-left support for Arabic, Hebrew, Persian, and Urdu. Auto language finding for mixed-language docs.
Deterministic Results
Regex patterns for set data give deterministic, reproducible results (same input + same ruleset version). ML-based NER provides high consistency for names. Fully audit-fit for audit fit.
Platform Components
Web Application
Cloud-Based Processing
Full-featured web interface with Zero-Knowledge sign-in. No software installation needed.
Desktop App
Windows 10+, macOS 10.15+, Linux (Ubuntu 20.04+)
Docs stay on your device while using cloud-powered item finding. Only extracted text is sent for study. AES-256-GCM encoding with Argon2id key derivation. Supports PDF, DOCX, XLSX, TXT, CSV, JSON, XML.
Office Add-in
Word, Excel & PowerPoint.
Real-time PII finding directly in Microsoft Office. Anonymize without leaving your document.
MCP Server
Claude Desktop, Cursor, VS Code (Continue & Cline)
Native stdio link-up for Claude Desktop. HTTP endpoints for Cursor and VS Code via Continue and Cline extensions. 6 operators with item groups and presets.
Chrome Extension Developer Preview
ChatGPT, Claude & Gemini.
Auto detect and anonymize PII before sending messages to AI chatbots. Real-time interception with response de-PII strip.
REST API
JWT Sign-in
RESTful endpoints for workflow auto-work and CI/CD pipeline link-up.
Batch Processing
Up to 100 Docs (Firm-wide)
Multi-document upload with parallel processing. Plan limits: Free (2), Basic (5), Pro (10), Biz (50).
Industries & Applications
Legal
Contract PII strip & e-scan. Redact touchy info from court filings and scan docs with audit trails.
Enterprise
GDPR audit fit at scale. Centralized PII finding across departments with role-based access control.
Healthcare
Patient data workflows matched to HIPAA PHI handling. Medical records PII strip for research and administrative docs.
Financial
PCI-DSS-matched PAN/PII redaction for fraud-prevention workflows. Deal and client data safety with rule-set reporting.
Government
Public records & FOIA audit fit. Auto-run redaction for FOIA requests and inter-agency data sharing.
Developers
Testing setups & CI/CD pipelines. Safe test dataset generation without live PII exposure.
Zero-Knowledge Architecture
Password Never Leaves Device
True Zero-Knowledge sign-in. Your master password is used locally to derive encoding keys. Server never sees your password.
Argon2id + XChaCha20-Poly1305
Argon2id (64 MB / 3 iterations) for memory-hard key derivation; XChaCha20-Poly1305 for authenticated encoding.
24-Word Recovery Phrase
BIP-39 compatible recovery phrase for account recovery. No password reset emails — you control your keys.
ISO 27001-Aligned
Hosted in Hetzner data centers in Germany. Designed for GDPR with EU data residency. ISO 27001 fit without a third-party certificate — framework controls set up, formal cert not yet obtained.
Transparent Token System
Think of tokens like game coins. Each operation costs tokens based on text length, items found, and ops applied. AI Item Creation costs 50 tokens per request.
Free
€0/month
200 tokens per 30-day cycle.
- Online account.
- Analyzer & Anonymizer.
- 48 languages
- Default presets.
- Batch processing (2 texts)
- TXT files only.
- 1 MB max file size.
Basic Most Popular
€3/month
1,000 tokens per 31-day cycle + top-ups (+250 for €1)
- All Free features.
- Batch processing (5 texts)
- Public presets & items.
- API access.
- PDF/DOCX/TXT/CSV support.
- 5 MB max file size.
- 50 files/day
Pro Best Value
€15/month
4,000 tokens per 31-day cycle + top-ups (+300 for €1)
- All Basic features.
- MCP Server access.
- Batch processing (10 texts)
- All file types supported.
- 10 MB max file size.
- Unlimited uploads.
Business Enterprise
€29/month
10,000 tokens per 31-day cycle + top-ups (+350 for €1)
- All Pro features.
- Batch processing (50 texts)
- 20 MB max file size.
- 1,000 history entries.
- Priority support.
- Custom link-ups.
anonym.legal vs anonymize.today
Both platforms share the same core technology but serve other use cases.
| Feature | anonym.legal | anonymize.today |
|---|---|---|
| Focus | Legal & Privacy-First. | Simple & Transparent. |
| Languages | 48 + RTL Support. | 27 |
| Item Types. | 285+ | 256 |
| Zero-Knowledge Auth. | Yes | No |
| MCP Server. | Yes (Claude, Cursor, VS Code + extensions) | No |
| Basic Tier Tokens. | 1,000 | 500 |
| Recovery Method. | 24-word phrase. | Email-based |
Try anonym.legal
Start with 200 free tokens per month. No credit card needed. Zero-Knowledge from day one.
Related Platform: anonymize.today — Firm-wide-grade PII finding with 256 item types
Best fit and known limitations
Best for
Legal, audit fit, and rule-bound teams that need verifiable Zero-Knowledge processing with native MCP link-up into Claude Desktop, Cursor, and VS Code; matters where audit trails and 48-language coverage including RTL scripts are non-negotiable.
Not the right fit
Casual single-user PII scrubbing without audit fit scope (use anonymize.today rather) or workflows that need image OCR redaction (use cloak.biz).
Known limitations
The free tier is capped at 200 tokens per month; the deterministic regex layer needs manual tuning for niche jurisdictional formats; ML name finding accuracy varies by language and perks from human review on long-tail surnames.
Need privacy-first data anonymization?
Let's discuss how anonym.legal can support your legal audit fit and Zero-Knowledge needs.