new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

mcp-sampling/capabilities

5 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

MCP Sampling supported AI SDK functions

The MCP Sampling provider supports generateText, streamText, structured output with Output, and experimental tool calling.

MCP Sampling no token counting limitation

MCP Sampling provider does not provide token usage information and returns 0 for token counts.

MCP Sampling no native streaming limitation

MCP Sampling does not support streaming natively. The provider calls doGenerate first, then emits the complete response as stream events.

MCP Sampling tool and JSON support via system prompt

Tool calling and JSON/structured output support in MCP Sampling is experimental and implemented via system prompt injection, as MCP Sampling does not natively support these features. This may not be as reliable as native tool support.

MCP Sampling request flow

The MCP Sampling provider processes requests as follows: (1) AI SDK calls the language model, (2) Provider converts to MCP sampling/createMessage format, (3) MCP client handles the sampling request and decides which actual model to use based on modelPreferences, (4) Provider converts response back to AI SDK format.

Give your agent this brain