redacta-mcp

MCPattested
v2.1.0Nick LambMIT-0Updated 1mo agonpmGitHub

MCP server that acts as a stateful privacy boundary: pseudonymises patient identifiers and PII before they reach an AI agent, keeps the reversal mapping outside the model context, and restores identifiers only at the trusted boundary. Runs locally, nothin

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Attested build
A verified provenance attestation binds this artifact to the listed repository. Nobody has claimed the listing yet — this proves where the code was built, not who stands behind it.
37Downloads/wk
9GitHub stars
1mo agoLast update
Package
AuthorNick Lamb
LicenseMIT-0
Version2.1.0
Sourcenpm+mcp-registry
Trust Status
A
85/100Trusted
✓Listed in Forge index+10/10
✓Identity verified · attested build+20/20
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
✓npm Trusted Publishing (Sigstore)+5/5
—npm maintainer match+0/5
→ Publisher: add the verified GitHub login to the npm package's maintainers (npm owner add <login>)
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusIdentity verified
PublisherUnverified
SignatureUnsigned
Domain—
Provenance✓ Sigstore-verified · f386d90
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface8 tools · none privileged
Security scan✓ Cleanv2.1.0 · 1mo agoHow well does this scan work?
EvalsNone
IndexedAug 11, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

8 tools · none privileged
Statically extracted from the published packagev2.1.0 · 1mo ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

protectNo description published

This tool published no description. Forge does not invent one.

release_to_fileNo description published

This tool published no description. Forge does not invent one.

release_to_clientNo description published

This tool published no description. Forge does not invent one.

check_outputNo description published

This tool published no description. Forge does not invent one.

discard_sessionNo description published

This tool published no description. Forge does not invent one.

redactNo description published

This tool published no description. Forge does not invent one.

reinstateNo description published

This tool published no description. Forge does not invent one.

self_checkNo description published

This tool published no description. Forge does not invent one.

0 of 8 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

MCP server that acts as a stateful privacy boundary: pseudonymises patient identifiers and PII before they reach an AI agent, keeps the reversal mapping outside the model context, and restores identifiers only at the trusted boundary. Runs locally, nothin

Keywords
mcpmodelcontextprotocolredactionpseudonymisationde-identificationpiiphihealthcarenhsprivacy
Alternatives
Comparing tool surfaces…

No dependency coverage

This package was last scanned before Forge began storing the resolved tree. The next scan will record it.