Sora
OpenAIOpenAI's video model: text or image in, short clip out, with storyboard control.
Wraps the YouTube Data API for search, channel and video metadata, and captions where available. The transcript path is the useful one for research; anything that resembles bulk media extraction runs into API limits…
Pulling transcripts, metadata, and channel lists for content research
Bulk downloading media — that is not what the API is for, and the terms say so
Wraps the YouTube Data API for search, channel and video metadata, and captions where available. The transcript path is the useful one for research; anything that resembles bulk media extraction runs into API limits and terms, which is worth reading before building on it.
uvx youtube-mcpPaste this into your MCP client config, then restart the client.
{
"mcpServers": {
"avbbc": {
"command": "npx",
"args": ["-y", "uvx youtube-mcp"]
}
}
}Queries the arXiv API for papers by topic, author, or identifier, and returns metadata plus abstracts. The practical warning is about citation: an abstract is a clai…
Reads Hacker News through its public API: top stories, item threads, and comment trees for a keyword. It is a cheap way to see what practitioners said about a tool, …
Reads channels and groups through the Bot API: recent messages, search, and posting. The distinction that matters is bot token versus user session — a bot sees what …
OpenAI's video model: text or image in, short clip out, with storyboard control.
Google DeepMind's video model, available through Gemini and Vertex AI.
Kuaishou's video generator, tuned for motion and image-to-video.
Turns a target query into a brief someone can write from.
Collects what changed on a competitor's site since the last scan.
Scores retrieval quality on a fixed question set.