What it does
The publisher describes AI Guard as a set of guardrails for code written by AI in JavaScript and TypeScript. The listed checks cover scans, detection of weakened tests, package checks, and a verification step before a task is considered done.
It fits a review step for AI-generated JavaScript or TypeScript before those changes are accepted.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 14 Nov 2026 · its page on the source
AI Guard
Guardrails for AI-written JS/TS: scans, weakened-test checks, package checks, verify before done.
v1.4.7As shown on registry.modelcontextprotocol.io when we last read it