Home / Servers / OpenAI API / create_run
Create run
An MCP tool from the OpenAI API server, hosted on mcp.hjlabs.in.
Create run Create a run. [POST /threads/{thread_id}/runs]
Name on the gateway: openai_api__create_run · may change things.
Parameters
| Name | Type | Description |
|---|---|---|
thread_id required | string | The ID of the thread to run. |
include[] | array | A list of additional fields to include in the response. Currently the only… |
assistant_id required | string | The ID of the assistant to use to execute this run. |
model | string | The ID of the Model to be used to execute this run. If a value is provided… |
reasoning_effort | none | minimal | low | medium | high | xhigh | max | Constrains effort on reasoning for reasoning models. Currently supported… |
instructions | string | Overrides the instructions of the assistant. This is useful for modifying the… |
additional_instructions | string | Appends additional instructions at the end of the instructions for the run.… |
additional_messages | array | Adds additional messages to the thread before creating the run. |
tools | array | Override the tools the assistant can use for this run. This is useful for… |
metadata | object | Set of 16 key-value pairs that can be attached to an object. This can be… |
temperature | number | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will… |
top_p | number | An alternative to sampling with temperature, called nucleus sampling, where… |
stream | boolean | If true, returns a stream of events that happen during the Run as server-sent… |
max_prompt_tokens | integer | The maximum number of prompt tokens that may be used over the course of the… |
max_completion_tokens | integer | The maximum number of completion tokens that may be used over the course of… |
truncation_strategy | object | Controls for how a thread will be truncated prior to the run. Use this to… |
tool_choice | object | Controls which (if any) tool is called by the model. none means the model will… |
parallel_tool_calls | boolean | Whether to enable parallel function calling during tool use. |
response_format | object | Specifies the format that the model must output. Compatible with GPT-4o, GPT-4… |
How to call it
Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:
{
"name": "openai_api__create_run",
"arguments": {
"thread_id": "…",
"assistant_id": "…"
}
}Or connect the OpenAI API server directly, which lists 371 tools including this one:
claude mcp add --transport http hj-openai-api https://mcp.hjlabs.in/mcp/openai-api \
--header "Authorization: Bearer YOUR_API_KEY"Try asking
Use the create run tool with thread_id set to ….