Skip to main content
View on GitHub → YouTube search results and rich metadata for autonomous agents. One AISA_API_KEY returns ranked videos, view counts, publication dates, and thumbnails — filterable by country and language.

​
Install

Start a new agent session after installing so the skill loads.

​
What can agents do with it?

Content gap analysis

“Find what’s ranking for ‘AI agent tutorial’ that our channel doesn’t cover.”

Competitor monitoring

“Track new uploads from the top 5 channels in this niche.”

Keyword research

“Which variations of ‘RAG’ pull the biggest view counts?”

Regional trends

“Surface top ML content in Japan (jp/ja) vs. the US (us/en).”

Audience research

“What thumbnails and titles work for agent demos?”

Trend spotting

“Flag videos with unusual velocity relative to channel baseline.”

​
Core capabilities

  • Keyword search — ranked YouTube results for any query
  • Regional targeting — gl (country: us, jp, cn, …) and hl (interface language: en, ja, zh-CN, …)
  • Rich metadata — titles, channels, view counts, publication dates, durations, thumbnails
  • Pagination — filter tokens for navigating beyond the first page

​
Quick start

​
Region + language

​
Pagination

The response includes a pagination token you can pass back to fetch the next page:

​
Python client

​
Endpoint reference

Common parameters:
  • engine — always youtube
  • q — search query (required)
  • gl — country code (us, jp, cn, etc.)
  • hl — language code (en, ja, zh-CN, etc.)
  • sp — pagination token

​
Get started

  1. Sign up at aisa.one and create an API key in the console.
  2. Set it in your shell: export AISA_API_KEY="your-key".
  3. Install the skill with one of the commands under Install, then start a new agent session.

YouTube Search endpoint

Full endpoint reference with interactive playground.

Multi-source Search

Combine YouTube search with web, scholar, and Tavily.

Error Codes

Handling YouTube API-level errors.