Implementation:Openai Openai python Tool Choice MCP Param

Knowledge Sources	Openai_Openai_python OpenAI API Reference
Domains	API_Types, Responses_API
Last Updated	2026-02-15 00:00 GMT

Overview

Concrete TypedDict for constructing an MCP tool choice parameter when sending requests to the Responses API, provided by the openai-python SDK.

Description

ToolChoiceMcpParam is a TypedDict used to build a tool choice configuration that forces the model to call a specific tool on a remote MCP (Model Context Protocol) server. It requires server_label (identifying which MCP server) and type (always "mcp"), with an optional name field to specify which tool on that server to invoke.

Usage

Import this type when constructing the tool_choice parameter for Responses API calls to force the model to use a specific MCP server tool.

Code Reference

Source Location

• Repository: openai-python
• File: src/openai/types/responses/tool_choice_mcp_param.py

Signature

class ToolChoiceMcpParam(TypedDict, total=False):
    """Use this option to force the model to call a specific tool on a remote MCP server."""

    server_label: Required[str]
    type: Required[Literal["mcp"]]
    name: Optional[str]

Import

from openai.types.responses import ToolChoiceMcpParam

I/O Contract

Fields

Name	Type	Required	Description
server_label	str	Yes	The label of the MCP server to use.
type	Literal["mcp"]	Yes	For MCP tools, the type is always mcp.
name	Optional[str]	No	The name of the tool to call on the server. If omitted, the model may choose any tool.

Usage Examples

from openai.types.responses import ToolChoiceMcpParam

mcp_choice: ToolChoiceMcpParam = {
    "type": "mcp",
    "server_label": "deepwiki",
    "name": "read_wiki_structure",
}

# Use as: client.responses.create(model="gpt-4o", input="...", tool_choice=mcp_choice)

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus