YT-NINJA
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TEMP_DIR | No | Temporary files directory | ./temp |
| LOG_LEVEL | No | Logging level (error, warn, info, debug) | info |
| DOWNLOAD_DIR | No | Directory for downloaded files | ./downloads |
| GEMINI_API_KEY | Yes | Google Generative AI API key for AI features | |
| MAX_CONCURRENT_DOWNLOADS | No | Maximum concurrent downloads | 3 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| play_youtube_videoB | Play YouTube video in browser or VLC |
| get_video_infoC | Get YouTube video information |
| get_playlist_infoC | Get YouTube playlist information |
| get_channel_infoC | Get YouTube channel information |
| search_youtubeC | Search YouTube |
| search_musicC | Search YouTube for music |
| download_thumbnailC | Download video thumbnail image |
| get_transcriptC | Get video transcript |
| translate_transcriptC | Translate video transcript |
| summarize_videoC | Generate AI summary of video |
| generate_chaptersC | Generate chapter markers for video |
| get_keywordsC | Extract keywords from video |
| detect_topicsC | Detect topics in video |
| generate_video_highlightsC | Generate AI-powered video highlights |
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 14 tools
Each tool has a clearly distinct purpose targeting specific YouTube-related actions or resources, such as detecting topics, downloading thumbnails, generating chapters/highlights, getting various types of information, searching, summarizing, and translating. There is no significant overlap or ambiguity between tools, making it easy for an agent to select the appropriate one.
All tool names follow a consistent verb_noun pattern using snake_case, such as 'detect_topics', 'download_thumbnail', 'get_channel_info', and 'search_youtube'. This uniformity enhances readability and predictability across the entire tool set.
With 14 tools, the server is well-scoped for YouTube content analysis and interaction, covering a comprehensive range of operations from information retrieval to AI-powered processing. Each tool serves a unique and justified function within this domain.
The tool set provides complete coverage for YouTube video and channel analysis, including CRUD-like operations (e.g., get info, search), AI enhancements (e.g., summarize, generate highlights), and utility functions (e.g., play video, translate transcript). There are no obvious gaps that would hinder agent workflows in this domain.