nickjlamb/redacta
by Various
Redacta — a Claude/Agent Skill that pseudonymises medical documents before AI processing
MCP
nickjlamb/redacta
Added 18 Oct 2026
Overview
Redacta is a Claude/Agent Skill that pseudonymises medical documents before AI processing. It replaces identifying information with synthetic identifiers, allowing medical text to be handled by AI services without exposing patient data. Written in TypeScript, it is designed to integrate into Claude or agent-based workflows.
Best for
Best for
Developers building Claude-based tools that handle medical data and need a lightweight pseudonymisation step.
Use cases
- Preprocess clinical notes for LLM analysis while preserving privacy
- Anonymize patient records before sharing with external AI tools
- Integrate privacy-preserving redaction into agent pipelines
Notes
8 stars on GitHub. Last updated 2026-10-06. Licensed MIT-0.
Pros
- Open source and available on GitHub for direct use and modification
- TypeScript implementation fits naturally into Node/TypeScript ecosystems
- Specifically designed for medical documents, addressing a compliance-sensitive niche
Cons
- Very early-stage project with only 8 stars, implying limited community validation
- Scope is narrow, focused on medical documents and Claude/Agent environments
- No evidence of standalone API use; installation and runtime depend on agent skill infrastructure
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.