yt-transcript-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 | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_transcriptA | Fetch a YouTube video transcript. Returns compact JSON (default) or markdown. Defaults to segments-only for token efficiency. Cached by language preference. Retries only transient errors. Includes provenance, caption type, and verifiable content hash. |
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 1 tool
With only one tool, there is no possibility of confusing it with another. The tool's purpose is narrowly and clearly defined.
The single tool name 'fetch_transcript' follows a clear verb_noun convention. There are no other names to contradict this pattern.
One tool is borderline for a server, but it is reasonable for a narrowly focused YouTube transcript service. It feels thin if broader video or transcript management is expected, though the scope appears intentionally minimal.
The tool covers the core need of fetching a transcript with useful options like markdown output, caching, and provenance. Minor gaps exist around listing available transcripts or explicitly choosing languages, but these are workable and not fatal for the stated purpose.