MCP server that searches YouTube through SerpApi
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"mcp-youtube-search","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# MCP YouTube Search <!-- mcp-name: io.github.arjunprabhulal/mcp-youtube-search --> An MCP server that searches YouTube through [SerpApi](https://serpapi.com/youtube-search-api), for Claude, Cursor and other MCP clients: titles, links, channels, views, publish dates, durations and descriptions. [](https://github.com/arjunprabhulal/mcp-youtube-search/actions/workflows/ci.yml) [](https://pypi.org/project/mcp-youtube-search/) ## Requirements - Python 3.10 or later (or [uv](https://docs.astral.sh/uv/)) - A SerpApi key in `SERP_API_KEY` (serpapi.com has a free tier) ## Use it from an MCP client ```json { "mcpServers": { "youtube-search": { "command": "uvx", "args": ["mcp-youtube-search", "server"], "env": { "SERP_API_KEY": "your-serpapi-key" } } } } ``` Or `pip install mcp-youtube-search` and use `"command": "mcp-youtube-search", "args": ["server"]`. ## Command line ```bash export SERP_API_KEY="your-serpapi-key" mcp-youtube-search search "model context protocol" --max-results 5 mcp-youtube-search server # MCP over stdio mcp-youtube-search server --connection_type http --port 3002 # Streamable HTTP at http://127.0.0.1:3002/mcp ``` `LOG_LEVEL=DEBUG` shows more detail on stderr. The API key is never logged. ## Tool | Tool | What it does | | --- | --- | | `search_youtube` | Videos for a query. `query`; optional `max_results` (1-50, default 10), `language` (default `en`), `country` (default `us`). Returns structured results: title, link, channel, views, publish date, duration, thumbnail, description. | ## Development ```bash uv sync uv run pytest uv run ruff check . ``` ## License MIT
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.