What it does
According to the publisher, RuleDrift tests whether AI agents keep critical instructions as a conversation gets longer. The entry covers only this description; no further documentation was available when it was written.
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 13 Nov 2026 · its page on the source
RuleDrift
Test whether AI agents retain critical instructions as conversations grow.
v0.1.1As shown on registry.modelcontextprotocol.io when we last read it