Implementation:Openai Openai python Response MCP Call Args Done

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

Overview

Concrete streaming event type for signaling that MCP tool call arguments have been finalized provided by the openai-python SDK.

Description

ResponseMcpCallArgumentsDoneEvent is a Pydantic model emitted when the arguments for an MCP tool call are finalized. It carries an arguments field containing the complete JSON string of finalized arguments, the item_id identifying the MCP tool call item, the output_index locating it in the response output array, and a sequence_number for event ordering. The type field is always "response.mcp_call_arguments.done".

Usage

Import this type when building streaming event handlers that need to detect when MCP tool call argument construction is complete, enabling you to parse the full arguments JSON and proceed with tool execution.

Code Reference

Source Location

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

Signature

class ResponseMcpCallArgumentsDoneEvent(BaseModel):
    """Emitted when the arguments for an MCP tool call are finalized."""

    arguments: str
    item_id: str
    output_index: int
    sequence_number: int
    type: Literal["response.mcp_call_arguments.done"]

Import

from openai.types.responses import ResponseMcpCallArgumentsDoneEvent

I/O Contract

Fields

Name	Type	Required	Description
arguments	str	Yes	A JSON string containing the finalized arguments for the MCP tool call.
item_id	str	Yes	The unique identifier of the MCP tool call item being processed.
output_index	int	Yes	The index of the output item in the response's output array.
sequence_number	int	Yes	The sequence number of this event.
type	Literal["response.mcp_call_arguments.done"]	Yes	The type of the event. Always response.mcp_call_arguments.done.

Usage Examples

import json
import openai

client = openai.OpenAI()

stream = client.responses.create(
    model="gpt-4o",
    input="Use the MCP tool to fetch data.",
    stream=True,
)

for event in stream:
    if event.type == "response.mcp_call_arguments.done":
        args = json.loads(event.arguments)
        print(f"Final arguments for item {event.item_id}: {args}")

Related Pages

• Environment:Openai_Openai_python_Python_3_9_Plus