Collected sources and patterns will appear here. Add from search or the patterns library.
SamplingParameters -> CreateSamplingMessage.Result
Delegate LLM generation requests from an untrusted server back to the host client for human-in-the-loop validation and execution.
Problem it solves
Dynamic tool servers need LLM intelligence, but granting them direct API access bypasses user boundaries, budget limits, and security controls.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.