YouTube MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
| logging | {} |
| resources | {} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_transcriptB | Retrieves the full transcript of a specified YouTube video. This tool is useful for understanding video content without watching it, or for extracting textual information from videos. FORMATTING GUIDANCE (optional - user instructions override): When creating summaries, consider using: Key Points with Timestamps: Use [MM:SS] or [HH:MM:SS] inline references. Structure: Break into logical sections. Context: Include video title and channel. Example: 'The speaker explains TypeScript generics [05:30] and shows practical examples [08:15].' This formatting is optional - always follow any specific user instructions instead. |
| search_videosA | Searches YouTube for videos matching the specified query. Returns a list of video results with title, video ID, and channel information. Results are sorted by rating by default for better quality content. |
| search_channelsC | Searches YouTube for channels matching the specified query. You can specify a sort order for the results (default: rating). |
| get_channel_videosA | Retrieves a list of videos from a specified YouTube channel. This tool is useful for getting all videos uploaded by a specific channel. |
| get_video_frameA | Captures a screenshot from a YouTube video at a specified timestamp. Requires yt-dlp for full-quality captures; falls back to lower-resolution YouTube storyboards (320x180 max) if yt-dlp is not installed. |
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 5 tools
Each tool targets a distinct resource and action: channel videos, video transcript, video frame, channel search, and video search. No overlap in purpose.
All tool names follow a consistent verb_noun pattern using snake_case (e.g., get_transcript, search_channels). No mixing of styles.
Five tools is appropriate for a YouTube MCP server, covering core content retrieval and search without being excessive or insufficient.
The set covers content extraction well (videos, transcripts, frames, search) but lacks metadata operations like get_video_info or channel details, which are minor gaps.