Topic Classification
/ai/topic-classificationAccess X data through superagnt: Topic Classification. Allows you to automatically extract meaning from text by identifying recurrent themes or topics. Responses are structured JSON for AI agents, analytics, and automation — one API key instead of juggling upstream accounts. Ideal when you need tweets, user profiles, followers, search, and hashtag streams programmatically.
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 "https://api.superagnt.com/ai/topic-classification?text=<text>" \
-H "Authorization: Bearer <YOUR_AGNTDATA_API_KEY>"Copy-paste prompt
Paste this into a coding agent. It connects the superagnt MCP server, finds the tool data_x_topic_classification_get_ai_topic_classification, and runs a first call — with the REST fallback if MCP is unavailable.
You are wiring up the superagnt "X (Twitter)" API to use this endpoint: Topic Classification.
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_x_topic_classification_get_ai_topic_classification
Call agnt_tools_search or agnt_tools_list_enabled to confirm it is available.
2. REST fallback (if you are not using MCP):
GET https://api.superagnt.com/ai/topic-classification
Header: Authorization: Bearer <YOUR_AGNTDATA_API_KEY>
Required parameters:
- text (string, required)
Optional parameters:
- (none)
3. COST & KEY. Each successful call costs $0.005 in credits. 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_x_topic_classification_get_ai_topic_classification), 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/social/x/endpoints/Topic_Classification_get__ai_topic_classification.md{
"name": "topic_classification_get_ai_topic_classification",
"description": "Allows you to automatically extract meaning from text by identifying recurrent themes or topics",
"parameters": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "query parameter",
"default": "The @Humane video is fascinating on so many levels. I think people miss the point about how emotionally empty it feels. It’s because smartphones sucked everything out of us. And their device is there to reconnect us to the world. It was purposely recorded this way."
}
},
"required": [
"text"
]
}
}| Name | In | Type | Required | Description |
|---|---|---|---|---|
text | query | string | required |
200
{
"type": "object",
"properties": {
"text": {
"type": "string"
},
"hash": {
"type": "string"
},
"trace_id": {
"type": "string"
},
"topics": {
"type": "array",
"items": {
"type": "object",
"properties": {
"label": {
"type": "string"
},
"confidence": {
"type": "number"
},
"rank": {
"type": "integer"
},
"label_id": {
"type": "integer"
}
}
}
},
"elapsed_time": {
"type": "number"
}
}
}Credits are deducted from your superagnt balance on each 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.