MCP Browser YouTube Transcript
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_transcriptC | Fetches the plain text transcript of a YouTube video. |
| get_timed_transcriptC | Fetches the transcript with timestamps. |
| get_video_infoC | Fetches metadata about the video. |
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 3 tools
Each tool has a clearly distinct purpose: get_timed_transcript retrieves transcript with timestamps, get_transcript retrieves plain text transcript, and get_video_info fetches metadata. There is no overlap or ambiguity between these functions.
All tool names follow a consistent verb_noun pattern using snake_case (get_timed_transcript, get_transcript, get_video_info). The naming is predictable and uniform throughout the set.
Three tools is appropriate for the server's purpose of accessing YouTube transcripts and video info, though it feels slightly minimal. Each tool earns its place, but there might be room for additional related functions like search or list operations.
The toolset covers the core needs for YouTube transcript and video metadata access well, with no obvious dead ends. However, there are minor gaps such as the inability to search for videos or handle playlist transcripts, which agents might need to work around.