ChatGPT app answer
/chatgpt-app-answerAsks ChatGPT a question the way a logged-out user in the chosen country would in the ChatGPT app, and returns the answer as Markdown in `result[0].markdown` with every source it cited in `result[0].sources[]` (each with `url`, `title` and `domain`), the web results it read in `result[0].search_results[]`, the follow-up queries it ran in `result[0].fan_out_queries[]` and the brands it named in `result[0].brand_entities[]`. Use it to see whether ChatGPT cites a site and how it describes a brand. A live answer can take up to 95 seconds; one that runs longer fails with an error and is not charged. An answer with no sources is a valid answer, not an error.
Call it over REST
Authenticate with a bearer token against https://api.superagnt.com. Swap the placeholders for your key and parameter values.
curl -s -X POST "https://api.superagnt.com/chatgpt-app-answer" \
-H "Authorization: Bearer <YOUR_AGNTDATA_API_KEY>" \
-H "Content-Type: application/json" \
-d '{ "keyword": "<string>" }'Copy-paste prompt
Paste this into a coding agent. It connects the superagnt MCP server, finds the tool data_seo_chatgpt_app_answer, and runs a first call — with the REST fallback if MCP is unavailable.
You are wiring up the superagnt_ "SEO" API to use this endpoint: ChatGPT app answer.
1. CONNECT over MCP (preferred). No token to paste either way.
On Claude (claude.ai, the desktop app, or Claude Code signed in with a Claude
account), the server is a connector: give the user this link, they click Add
and approve:
https://claude.ai/customize/connectors/yours?modal=add-custom-connector&connectorName=superagnt&connectorUrl=https%3A%2F%2Fmcp.superagnt.com%2Fmcp&open_in_browser=1
Any other MCP client (or Claude Code signed in with an API key): add the server
and let the client run the browser sign-in:
claude mcp add --scope user --transport http superagnt https://mcp.superagnt.com/mcp
claude mcp login superagnt
MCP endpoint: https://mcp.superagnt.com/mcp
After connecting, the tool you want is named exactly:
data_seo_chatgpt_app_answer
Call agnt_tools_search or agnt_tools_list_enabled to confirm it is available.
2. REST fallback (if you are not using MCP):
POST https://api.superagnt.com/chatgpt-app-answer
Header: Authorization: Bearer <YOUR_AGNTDATA_API_KEY>
Required parameters:
- keyword (string, required) — The question to ask ChatGPT, as a user would type it.
Optional parameters:
- location_code (integer, optional) — Geo target as a location code. Common values: 2840 United States (default), 2826 United Kingdom, 2124 Canada, 2036 Australia, 2276 Germany.
- language_code (string, optional) — Two-letter language code, e.g. 'en' (default).
- force_web_search (boolean, optional) — Push ChatGPT to search the web and cite current sources. Citations are still not guaranteed.
3. COST & KEY. This endpoint is metered — pricing varies by request, from $0.002 per call. Only successful calls are charged.
Get a superagnt_ API key at https://app.superagnt.com.
4. TEST. Connect the server (or set the key), discover the tool
(data_seo_chatgpt_app_answer), run one minimal call with just the required parameters,
and report back the shape of the JSON response (top-level fields).
Reference (machine-readable variant): https://www.superagnt.com/docs/apis/seo/endpoints/chatgpt_app_answer.md{
"name": "chatgpt_app_answer",
"description": "Asks ChatGPT a question the way a logged-out user in the chosen country would in the ChatGPT app, and returns the answer as Markdown in `result[0].markdown` with every source it cited in `result[0].sources[]` (each with `url`, `title` and `domain`), the web results it read in `result[0].search_results[]`, the follow-up queries it ran in `result[0].fan_out_queries[]` and the brands it named in `result[0].brand_entities[]`. Use it to see whether ChatGPT cites a site and how it describes a brand. A live answer can take up to 95 seconds; one that runs longer fails with an error and is not charged. An answer with no sources is a valid answer, not an error.",
"parameters": {
"type": "object",
"properties": {
"keyword": {
"type": "string",
"maxLength": 2000,
"description": "The question to ask ChatGPT, as a user would type it."
},
"location_code": {
"type": "integer",
"description": "Geo target as a location code. Common values: 2840 United States (default), 2826 United Kingdom, 2124 Canada, 2036 Australia, 2276 Germany.",
"default": 2840
},
"language_code": {
"type": "string",
"description": "Two-letter language code, e.g. 'en' (default).",
"default": "en"
},
"force_web_search": {
"type": "boolean",
"default": false,
"description": "Push ChatGPT to search the web and cite current sources. Citations are still not guaranteed."
}
},
"required": [
"keyword"
]
}
}| Name | In | Type | Required | Description |
|---|---|---|---|---|
keyword | body | string | required | The question to ask ChatGPT, as a user would type it. |
location_code | body | integer | optional | Geo target as a location code. Common values: 2840 United States (default), 2826 United Kingdom, 2124 Canada, 2036 Australia, 2276 Germany. |
language_code | body | string | optional | Two-letter language code, e.g. 'en' (default). |
force_web_search | body | boolean | optional | Push ChatGPT to search the web and cite current sources. Citations are still not guaranteed. |
ChatGPT's answer in `result[0].markdown`, its cited sources in `result[0].sources[]`.
{
"type": "object"
}Metered endpoint — the exact cost depends on the request. Credits are deducted per successful call; failed requests (4xx/5xx) are not charged.
Get started at app.superagnt.com.
start calling
Point your client at https://mcp.superagnt.com/mcp and your agent has this endpoint, plus every other source on one balance.