gpt_search_batch
Run multiple ChatGPT search/research prompts in parallel, each in its own tab, and collect responses into a single summary.
Instructions
Run multiple ChatGPT search/research prompts concurrently.
Each request opens its own ChatGPT tab and runs concurrently with the others. This is the text equivalent of gpt_image_gen_batch. The server runs at most 3 ChatGPT tabs at a time across all calls and sessions; larger batches queue internally.
Each item in requests is a dict with keys:
query(optional, str): the full promptprompt_file(optional, str): path to a text file containing the promptoutput_file(optional, str): path where the cleaned markdown response should be savedlabel(optional, str): heading used for this item in the combined response; defaults tooutput_file, thenprompt_file, thenrequest_<n>return_output(optional, bool): overrides the batch-levelreturn_outputfor this itemoutput_json(optional, bool): overrides the batch-leveloutput_jsonfor this item
Provide either query or prompt_file for each item. Relative file paths resolve from the MCP server process working directory.
return_output is batch-level unless overridden per item. When omitted, each item defaults to returning the full output only if it has no output_file.
output_json is batch-level unless overridden per item. When enabled, the response is parsed/repaired after ChatGPT returns. For file outputs, raw output is saved first and overwritten only when JSON post-processing succeeds.
Returns a markdown summary. If outputs are returned, they are grouped under per-request headings.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| requests | Yes | ||
| return_output | No | ||
| output_json | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |