YouTube MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| YOUTUBE_API_KEY | Yes | Your YouTube Data API v3 key, obtained from the Google Cloud Console. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_youtubeB | Search YouTube for videos by keyword. Returns video metadata including title, channel, views, and thumbnails. |
| get_video_detailsB | Get comprehensive metadata about a specific YouTube video including title, description, duration, views, likes, tags, and thumbnails. |
| get_video_transcriptB | Fetch the transcript/captions for a YouTube video. Returns the full text with timestamps. Useful for video summarization and content analysis. |
| get_channel_infoC | Get detailed information about a YouTube channel including subscriber count, video count, view count, and optionally recent videos. |
| get_channel_videosB | List videos from a specific YouTube channel. Returns video metadata sorted by date, view count, or title. |
| get_playlist_infoA | Get information about a YouTube playlist including title, description, video count, and channel details. |
| get_playlist_videosA | List all videos in a YouTube playlist with their metadata and position in the playlist. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose targeting different YouTube resources: channel info, channel videos, playlist info, playlist videos, video details, video transcripts, and general search. There is no overlap in functionality, making tool selection straightforward for an agent.
All tools follow a consistent verb_noun pattern with 'get_' or 'search_' prefixes (e.g., get_channel_info, search_youtube). The naming is uniform and predictable, enhancing usability and reducing cognitive load.
With 7 tools, the server is well-scoped for YouTube operations. Each tool serves a distinct and essential function in the domain, providing comprehensive coverage without being overwhelming or sparse.
The toolset covers core YouTube operations like retrieving channel, playlist, video, and transcript data, plus search. Minor gaps exist, such as no tools for creating or managing content (e.g., upload, comment, like), but these are likely outside the server's read-only scope, and agents can work effectively with the provided tools.