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 in search.
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 "Install 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.
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.
🔎 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
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.
Tool | Description |
| Semantic search. Empty |
| The canonical topic labels for the |
search returns {results: [{title, url, channel, topics, published_at, summary}], count, quota_remaining}.
"Find recent videos about building autonomous coding agents."
search(query="autonomous coding agents", lang="en", limit=5)Env var | |
| Your Pro API key (required). |
| Override the API base (default |
🌐 Homepage & subscription: https://aidevtube.com
MIT licensed.
List the canonical topic labels usable in the topics filter of search.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not explicitly state that the operation is read-only or idempotent. However, 'list' implies a read operation, and the tool has no parameters, so behavioral complexity is low. The description could be more explicit about side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the verb and resource, with no unnecessary words. Every word contributes to understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and an output schema exists, the description is fully complete. It explains the purpose and relationship to the sibling tool, which is all that is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and schema coverage is 100% trivially. The description does not need to add parameter semantics, so baseline 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists canonical topic labels usable in the 'topics' filter of the sibling tool 'search'. It specifies the verb 'list' and the resource 'canonical topic labels', distinguishing it from the sibling tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly indicates that the output is for use in the 'topics' filter of 'search', providing clear context for when to use this tool. It does not explicitly state when not to use it, but the context is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the AI YouTube Digest corpus (per-video summaries from ~40 curated AI/coding channels).
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Free-text semantic query (e.g. "autonomous coding agents"). Empty = browse newest by filters. | |
| topics | No | Comma-separated topic filter (OR). Use `list_topics` for valid labels. | |
| channel | No | Exact channel name filter (e.g. "Nate Herk | AI Automation"). | |
| lang | No | Summary language — "en", "de" or "fr". | en |
| limit | No | Max results, 1-50. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are missing, so the description must cover behavioral traits. It states the tool is for searching but does not mention if it's read-only, authentication needs, rate limits, or how empty queries behave (though schema parameter description mentions browsing newest). Lack of annotations means this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 12 words, front-loaded with the action and resource. Every word earns its place with zero fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simple tool with 5 documented parameters and an output schema, the description is mostly complete. It identifies the corpus and its scope. Minor gap: no mention of the curated nature or that it only covers recent videos, but schema covers parameter details.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the baseline is 3. The description does not add semantic value beyond the schema, but the schema itself is well-documented.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it searches a specific corpus (AI YouTube Digest) with per-video summaries from ~40 curated AI/coding channels. The action and resource are specific, and the sibling tool list_topics is complementary for topic labels, so distinction is clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like list_topics, nor any prerequisites or conditions. The context is implied but not explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0list_topicssearchlist_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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Personal YouTube AI knowledge base powered by RAG. Query your subscribed YouTube channels.
Transcribe YouTube via Whisper. Summaries, chapters, semantic-search across your corpus.
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents. No signup.
YouTube video search with transcript extraction as first-class output.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/miraculix95/aidevtube-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
