YouTube Summary MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LOG_LEVEL | No | Logging level: DEBUG, INFO, WARNING, ERROR, CRITICAL | INFO |
| MCP_SSE_HOST | No | Bind host for SSE server | 0.0.0.0 |
| MCP_SSE_PATH | No | SSE endpoint path | /sse |
| MCP_SSE_PORT | No | Bind port for SSE server | 10719 |
| SUMMARY_RATIO | No | Ratio of original length for summary (e.g., 0.35 means 35%) | 0.35 |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_transcriptA | Fetch the transcript of a YouTube video. Args: video_url: YouTube URL or video ID language: Language code (default: en) Returns: Transcript text |
| summarize_videoB | Generate a summary of a YouTube video. Args: video_url: YouTube URL or video ID summary_length: Summary length (short, medium, long) language: Language code (default: en) Returns: Summary text |
| extract_key_pointsB | Extract key points from a YouTube video. Args: video_url: YouTube URL or video ID num_points: Number of key points to extract (default: 5) language: Language code (default: en) Returns: Formatted key points |
| get_video_metadataA | Get metadata (title, channel, etc.) of a YouTube video. Args: video_url: YouTube URL or video ID Returns: Formatted metadata |
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 targets a distinct output type: transcript, summary, key points, and metadata. There is no overlap in purpose, and the descriptions clearly differentiate them.
All tools follow a consistent verb_noun pattern (get_transcript, summarize_video, extract_key_points, get_video_metadata) using snake_case. The naming is uniform and predictable.
With 4 tools, the server is well-scoped for a YouTube summary MCP. Each tool covers a fundamental operation without unnecessary bloat or thinness.
The toolset provides a complete lifecycle for the stated purpose: fetching transcript, generating summary, extracting points, and retrieving metadata. No obvious gaps exist for a summary-focused server.