aidevtube-mcp
This server enables semantic search and browsing of a curated, multilingual corpus of AI and coding YouTube video summaries (~40 hand-picked channels). It provides two tools:
search: Query videos using natural language (hybrid vector search + rerank). Leave the query empty to browse the newest content. Supports:Topic filtering: Narrow results by comma-separated topic labels (e.g., "Claude Code & Anthropic-Tooling") with OR logic.
Channel filtering: Restrict results to a specific channel by exact name.
Language: Retrieve summaries in English (
en), German (de), or French (fr).Result count: Control how many results are returned (1–50).
Each result includes the video title, URL, channel name, topics, publication date, and a per-video summary.
list_topics: Retrieve the canonical list of available topic labels to use as filters insearch.
The server works as a drop-in MCP interface for Claude Desktop, Claude Code, Cursor, and any MCP-compatible client.
Semantic search over a longitudinal corpus of per-video summaries from ~40 curated AI/coding YouTube channels, with filtering by topics, channel, and language.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@aidevtube-mcp search for videos about AI agent workflows"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
aidevtube-mcp
Semantic search over the entire AI & coding YouTube landscape — right inside your LLM.
aidevtube-mcp is the official MCP server for the AI YouTube Digest —
a continuously growing, topic-tagged, multilingual corpus of per-video summaries from ~40
hand-curated AI & coding YouTube channels (Nate Herk, Tech With Tim, Theo, NeuralNine, WorldofAI,
and many more), updated every week.
Stop scrubbing through hours of video. Ask your agent "what did the AI-dev world say about Claude Code agents this month?" and get straight, sourced answers — searched by meaning, not keywords, across the whole back-catalogue.
Why it's useful
🔎 Semantic search (hybrid vector + Cohere rerank) — finds videos by what they're about, not just exact words.
🗓️ Longitudinal — a week-by-week map of the AI/coding discourse, not just today's hype. Pro keys search the full archive.
🏷️ Topic & channel filters — narrow to "Claude Code & Anthropic-Tooling", a specific creator, etc.
🌍 Multilingual — summaries in English, German and French.
🔌 Drop-in — works in Claude Code, Claude Desktop, Cursor, or any MCP client. There's also a plain REST API (
api.aidevtube.com).
Related MCP server: YouTube Tools MCP Server
Quick start
Add to your MCP client (Claude Desktop / Claude Code / Cursor):
{
"mcpServers": {
"aidevtube": {
"command": "uvx",
"args": ["aidevtube-mcp"],
"env": { "AIDEVTUBE_API_KEY": "adt_your_key_here" }
}
}
}Or run it directly:
AIDEVTUBE_API_KEY=adt_… uvx aidevtube-mcpGet an API key: subscribe to Pro at aidevtube.com (€/$5 per month, incl. 1,000 API calls/month) → Account → API → generate your key.
Tools
Tool | Description |
| Semantic search. Empty |
| The canonical topic labels for the |
search returns {results: [{title, url, channel, topics, published_at, summary}], count, quota_remaining}.
Example
"Find recent videos about building autonomous coding agents."
search(query="autonomous coding agents", lang="en", limit=5)Configuration
Env var | |
| Your Pro API key (required). |
| Override the API base (default |
Links
🌐 Homepage & subscription: https://aidevtube.com
MIT licensed.
Available Tools
2 toolslist_topicsA
List the canonical topic labels usable in the topics filter of search.
Inputs: no named parameters. Returns: object
searchB
Search the AI YouTube Digest corpus (per-video summaries from ~40 curated AI/coding channels).
Inputs: query, topics, channel, lang, +1 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
list_topics and search serve distinct, complementary purposes: one enumerates filter labels, the other performs queries. No overlap exists.
Both use snake_case, but list_topics follows verb_noun pattern while search is a single verb. Slight inconsistency but still predictable.
With only 2 tools, the server is minimal but focused. The tools directly support the core functionality of browsing topics and searching the corpus.
The surface covers listing topics and searching, but lacks direct retrieval of full video summaries or details beyond search results, which agents may need.
Related MCP Connectors
Personal YouTube AI knowledge base powered by RAG. Query your subscribed YouTube channels.
YouTube transcripts, search, and channel and playlist listings for any AI app. Hosted.
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents.
Transcribe YouTube via Whisper. Summaries, chapters, semantic-search across your corpus.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceBuilds a searchable knowledge base from YouTube video transcripts with hybrid semantic and keyword search. Allows LLM assistants to search, organize, and retrieve timestamped information from videos you've watched.3-
- AlicenseBqualityDmaintenanceEnables AI assistants to search YouTube videos using the official YouTube Data API v3, extract full video transcripts in multiple languages, and store/retrieve video summaries using a local database.4MIT
- AlicenseAqualityCmaintenanceConnect AI assistants to YouTube: search, transcripts, metadata, and more.1988 npm6MIT
- AlicenseAqualityDmaintenanceEnables AI assistants to search YouTube, fetch transcripts, and get AI summaries of videos without API keys.36 npmMIT