MCP YouTube Transcript Pro
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 |
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 |
|---|---|
| list_tracksB | Lists available caption tracks for a YouTube video |
| get_transcriptC | Returns a merged plain text transcript |
| get_timed_transcriptA | Returns timestamped transcript segments in multiple formats (JSON, SRT, VTT, CSV, TXT) with optional preprocessing |
| get_video_infoA | Returns video metadata including title, channel, duration, and available captions |
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 4 tools
Each tool serves a clearly distinct purpose: list_tracks enumerates available caption tracks, get_video_info retrieves metadata, get_transcript returns plain text, and get_timed_transcript provides timestamped segments. There is no overlap or ambiguity, as descriptions explicitly differentiate between plain and timed transcripts.
All tool names follow a consistent verb_noun pattern using snake_case (get_timed_transcript, get_transcript, get_video_info, list_tracks). The verbs 'get' and 'list' are standard and unambiguous, creating a predictable naming scheme.
Four tools are well-suited for a YouTube transcript server, covering core functionality without unnecessary bloat. The count is sufficient for the domain and allows agents to efficiently accomplish transcript-related tasks.
The toolset covers the full lifecycle of transcript retrieval: listing available tracks, fetching metadata, and retrieving both plain and timestamped transcripts. No essential operations are missing for the stated domain.