Provided by TikHub
X search
Search on X: one page of about 15 to 20 posts for a keyword, with data.next_cursor for the next page. search_type is Top (the default), Latest, Media, People or Lists. from:handle with since:YYYY-MM-DD and until:YYYY-MM-DD reaches an account's older posts, reposts included. X matches more than the post text (the quoted post, a linked article, media, the account), so a result can be a valid match without the keyword in its text; do not drop such results. This search leaves out most of an account's replies to other accounts; for those use /api/v1/twitter/web/fetch_user_tweet_replies. One request per call; TikHub bills the request whether or not data comes back, and an empty data envelope is reported as no result.
How to run it
Step 1Set up
Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.
set up https://glasser.ai/SKILL.md
Show me how to use the TikHub endpoint /api/v1/twitter/web/fetch_search_timeline on Glasser.glasser run -p tikhub -e '/api/v1/twitter/web/fetch_search_timeline' -i '{"keyword":"Elon Musk"}' --endpoint-version 1Uses endpoint version 1. Inspect the current price before running. Install and log in first on Get Started.
Once per Run:
IDEMPOTENCY_KEY=$(uuidgen)Run it, and copy this same block to send it again:
curl -X POST https://api.glasser.ai/v1/runs \
-H "Authorization: Bearer gl_..." \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"provider":"tikhub","endpoint":"/api/v1/twitter/web/fetch_search_timeline","input":{"keyword":"Elon Musk"},"endpoint_version":1}'Reuse the same Idempotency-Key to send it again: the second send is a read of the first Run. A new key is a new Run and a new Charge. Uses endpoint version 1; inspect the current price before running.
Step 2Try a specific example task
When you need to research a question, you might search for relevant sources and review which results are worth reading more closely.
Copy this prompt into your agent to find sources for your research question.
Use tikhub:/api/v1/twitter/web/fetch_search_timeline on Glasser.
Search for sources about my research question and explain which returned results are relevant.Endpoint structure
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"keyword"
],
"properties": {
"cursor": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "Cursor, default is None, used for paging, obtained from the last request"
},
"keyword": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "Search keyword"
},
"search_type": {
"type": "string",
"maxLength": 2048,
"minLength": 1,
"description": "Search type, default is Top, other optional values are Latest, Media, People, Lists"
}
},
"additionalProperties": false
}{
"keyword": "Elon Musk"
}This Endpoint publishes no output schema. You get the Provider's own response body, unchanged — we do not warrant a shape we cannot guarantee.
How pricing works
| Data returned or no match | The same price with or without matching data. | $0.0011 |
|---|---|---|
| Provider error | The Provider failed to answer. | $0.00 |
| Timed out | The Run exceeded its time limit. | $0.00 |
| Internal failure | An internal error prevented completion. | $0.00 |