Skip to content

MCP improvement: server support for sampling #1272

Open
@samuelcolvin

Description

@samuelcolvin

When using a pydantic-ai agent within an MCP server, we should be able to register a model that uses sampling to call back to the client for LLM requests.

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions