What it does
The publisher describes Stet as guardrails for AI coding agents, with a scope guard and locked behaviours. The agents it names are Claude Code, Cursor and Codex.
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 15 Nov 2026 · last seen 19 Nov 2026 · its page on the source
Stet
Guardrails for AI coding agents: scope guard and locked behaviours for Claude Code, Cursor, Codex
v0.7.2As shown on registry.modelcontextprotocol.io when we last read it