Struct SamplingRequest 

pub struct SamplingRequest {
    pub messages: Vec<PromptMessage>,
    pub max_tokens: u32,
    pub system_prompt: Option<String>,
}

A request to ask the connected MCP client to run LLM inference (“sampling”) — build one and pass it to McpContext::sample.

messages reuses PromptMessage rather than introducing a near-identical type — the spec’s sampling message shape ({"role":...,"content":{"type":"text",...}}) is exactly what PromptMessage already models.

Fields

messages: Vec<PromptMessage>

max_tokens: u32

system_prompt: Option<String>

An optional system prompt to steer the client’s model, per the spec’s params.systemPrompt.