Use case, X (Twitter) search

X (Twitter) search API for your agent. One call per search.

Send a search query with optional operators. Read post text and author back. Your agent picks the provider, and you pay per call.

Give this to your agent
set up looot - https://looot.ai/skill.md

The job

What the X (Twitter) search API gives your agent

X search finds what people are saying, with the operators power users know: from:, since:, until: and a minimum like count. Your agent sends the query and reads back the posts with their text, author and engagement. It is the base for brand monitoring, customer research and finding the posts worth replying to.

Three providers answer. One accepts the full advanced-search syntax inline and returns about 20 posts per page. One takes the filters as separate fields: exact phrase, any of these words, from these accounts, language, media type and a minimum of likes or replies. One takes a keyword and a search type.

You give

a search query with optional operators

claude code min_faves:50

You get

  • Post text
  • Author
  • Likes, replies and reposts
  • Post date
  • Post link

Sample calls

The request and what comes back

Each run is one POST to /v1/runs with an endpoint id and an input. These are illustrative calls with generic values. The run's result holds the provider's own fields.

Request
{"endpointId":"anyapi-run-twitter-search","input":{"query":"claude code min_faves:50","limit":20},"wait":30}
ResponseSample output
// POST /v1/runs, then read run.status and run.result
// result: accepts the full X advanced-search syntax in the query, returns posts with text, author and engagement, and pages with a cursor

The prompt

Copy one prompt, give it to your agent.

Edit the names and numbers, paste it, and the agent runs the job and shows the cost.

  • One run is one search.
  • 1 steps across 3 providers.
  • Runs on demand, whenever you ask.
Prompt: X (Twitter) search API
Use looot to search X for claude code min_faves:50 over the last month, and return the text, author, likes and link of each post. 1. Set up https://looot.ai/skill.md. 2. Search the catalog for each step and check its price before you call. 3. Run the cheapest endpoint that fits. 4. Show the results as a table and the total cost.

Give this to your agent
Setup command
set up looot - https://looot.ai/skill.md

Before you start

Settle these before the first run

  • Write the query with operators. Bare terms match broadly, and from:, min_faves: and a date window cut a search to the posts that matter.
  • Page with a cursor. A page holds about 20 posts on one provider, and a longer pull means several calls.
  • Be careful with replies. A search that mixes posts and replies is noisy, so use the media and engagement filters.

FAQ

Questions people ask

Find the posts worth a reply, follow mentions of a brand and collect the questions people ask. Your agent keeps the post link as the source.

For agents
use case
X (Twitter) search API
run
search
schedule
on demand
step
Search posts on X: anyapi anysite tikhub
setup
https://looot.ai/skill.md
llms.txt
https://looot.ai/llms.txt
updated
2026-10-04
markdown /use-cases/twitter-search-api.md

Try X (Twitter) search with your own agent.

Start your workspace, top up, and paste the prompt into the agent you already use.

Start your workspace See agent recipes