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 | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": true
} |
| resources | {
"subscribe": false,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_transcriptC | Get transcript text from a YouTube video. |
| get_video_infoC | Get metadata from a YouTube 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 2 tools
The two tools target clearly different outputs: transcript text versus video metadata. There is no realistic chance of an agent confusing them.
Both tools use the same get_<noun> snake_case pattern, which is perfectly consistent.
Two tools is thin for a server, though each one earns its place for a transcript-and-metadata use case. It feels more like a minimal utility than a full YouTube surface.
Core read operations for a single video are covered, but there is no way to search videos, list channel or playlist content, or discover videos, so agents cannot go from a topic to a video ID. For a read-only extraction tool this is workable but has notable gaps.