MCP YouTube Intelligence
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MYI_YT_DLP | No | Path to the yt-dlp executable | yt-dlp |
| MYI_STORAGE | No | Storage backend: sqlite or postgres | sqlite |
| MYI_DATA_DIR | No | Data directory | ~/.mcp-youtube-intelligence |
| GOOGLE_API_KEY | No | Google API key | |
| MYI_VLLM_MODEL | No | vLLM model name | |
| OPENAI_API_KEY | No | OpenAI API key | |
| MYI_SQLITE_PATH | No | SQLite database path | {DATA_DIR}/data.db |
| MYI_GOOGLE_MODEL | No | Google model to use | gemini-2.0-flash |
| MYI_LLM_PROVIDER | No | LLM provider to use: auto, openai, anthropic, google, ollama, vllm, lmstudio | auto |
| MYI_MAX_COMMENTS | No | Maximum number of comments to process | 20 |
| MYI_OLLAMA_MODEL | No | Ollama model name | llama3.1:8b |
| MYI_OPENAI_MODEL | No | OpenAI model to use | gpt-4o-mini |
| MYI_POSTGRES_DSN | No | PostgreSQL DSN | |
| ANTHROPIC_API_KEY | No | Anthropic API key | |
| MYI_VLLM_BASE_URL | No | vLLM base URL | http://localhost:8000 |
| MYI_LMSTUDIO_MODEL | No | LM Studio model name | |
| MYI_ANTHROPIC_MODEL | No | Anthropic model to use | claude-sonnet-4-20250514 |
| MYI_OLLAMA_BASE_URL | No | Ollama base URL | http://localhost:11434 |
| MYI_LMSTUDIO_BASE_URL | No | LM Studio base URL | http://localhost:1234 |
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 |
|---|---|
| get_videoB | Get video metadata + summary (~300 tokens). Provide a YouTube video ID. |
| get_transcriptA | Get video transcript. mode: 'summary' (default, ~300 tokens), 'full' (saves to file, returns path), 'chunks' (split into segments). |
| get_commentsC | Get top comments for a video. Optionally summarize them. |
| monitor_channelB | Monitor a YouTube channel via RSS. action: 'add' (subscribe), 'check' (poll for new videos), 'list' (show subscriptions), 'remove' (unsubscribe). |
| search_transcriptsB | Search stored transcripts by keyword. Returns matching snippets. |
| extract_entitiesC | Extract structured entities (companies, indices, people, sectors, etc.) from a video transcript. |
| segment_topicsC | Segment a video transcript into topics based on transition markers. |
| search_youtubeB | Search YouTube videos by keyword. Returns metadata list (~200 tokens). |
| get_playlistC | Get playlist metadata and video list from a YouTube playlist. |
| generate_reportB | Generate a structured markdown report for a YouTube video. Includes summary, topic segments, entities, and optionally comments. |
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 10 tools
Each tool has a clearly distinct purpose targeting specific YouTube-related tasks, such as extracting entities, generating reports, fetching comments, retrieving transcripts, and monitoring channels. There is no overlap in functionality, making it easy for an agent to select the correct tool without confusion.
All tool names follow a consistent verb_noun pattern using snake_case, such as 'extract_entities', 'generate_report', and 'get_transcript'. This uniformity enhances readability and predictability across the entire tool set.
With 10 tools, the server is well-scoped for YouTube intelligence tasks, covering key areas like video metadata, transcripts, comments, playlists, search, and monitoring. Each tool serves a unique and necessary function without being excessive or insufficient.
The tool set provides comprehensive coverage for YouTube video analysis, including data retrieval (video, transcript, comments), processing (entities, topics, reports), search (transcripts, YouTube), and monitoring (channel RSS). There are no apparent gaps that would hinder an agent's workflow.