Sentiment Analysis
/ai/sentiment-analysisAccess X data through agntdata: Sentiment Analysis. Analyze text to determine if the emotional tone of the message is positive, negative, or neutral. 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.agntdata.dev. Swap the placeholders for your key and parameter values.
curl -s "https://api.agntdata.dev/ai/sentiment-analysis?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_sentiment_analysis_get_ai_sentiment_analysis, and runs a first call — with the REST fallback if MCP is unavailable.
You are wiring up the agntdata "X (Twitter)" API to use this endpoint: Sentiment Analysis.
1. CONNECT over MCP (preferred). Add the superagnt MCP server, then let the client
run OAuth on first tool call — no token to paste:
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_sentiment_analysis_get_ai_sentiment_analysis
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.agntdata.dev/ai/sentiment-analysis
Header: Authorization: Bearer <YOUR_AGNTDATA_API_KEY>
Required parameters:
- text (string, required)
Optional parameters:
- (none)
3. COST & KEY. This endpoint is priced per call in credits, and each successful response reports its own cost in its meta.costCents field. Only successful calls are charged.
Get an agntdata API key at https://app.agntdata.dev.
4. TEST. Connect the server (or set the key), discover the tool
(data_x_sentiment_analysis_get_ai_sentiment_analysis), 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://superagnt.com/docs/apis/social/x/endpoints/Sentiment_Analysis_get__ai_sentiment_analysis.md{
"name": "sentiment_analysis_get_ai_sentiment_analysis",
"description": "Analyze text to determine if the emotional tone of the message is positive, negative, or neutral.",
"parameters": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "query parameter",
"default": "You can not be a platform that allows almost every opinion to be aired and lose traffic. People want to share their opinion on platforms they know freedom of speech exists to a very large extent. I get 99% of my news here on X, which is like days ahead of traditional media."
}
},
"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"
},
"sentiment": {
"type": "object",
"properties": {
"value": {
"type": "string"
},
"confidence": {
"type": "number"
}
}
},
"elapsed_time": {
"type": "number"
}
}
}This endpoint is priced per call and deducted from your agntdata balance; only a successful call is billed. Every billable response reports its own cost in meta.costCents.
Get a key at app.agntdata.dev.
start calling
Point your client at https://mcp.superagnt.com/mcp and your agent has this endpoint, plus every other source on one balance.