tube-bridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| YOUTUBE_API_KEY | No | Your YouTube Data API v3 key. Optional, unlocks 3 extra tools and higher-quality results. | |
| TUBE_BRIDGE_PROXY | No | Residential proxy URL (e.g., http://user:pass@geo.iproyal.com:12321). Recommended for transcript fetching on cloud deployments. | |
| TUBE_BRIDGE_AUTH_KEY | No | API key for protecting /mcp and /sse endpoints. If set, requests require Authorization: Bearer <key>. | |
| TUBE_BRIDGE_EMBEDDING_MODEL | No | Embedding model name (default: BAAI/bge-small-en-v1.5). | BAAI/bge-small-en-v1.5 |
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 |
|---|---|
| youtube_searchA | Search YouTube videos. Uses Data API v3 when YOUTUBE_API_KEY is set, falls back to yt-dlp. Filters: date range, channel, duration, order. |
| youtube_search_channelsA | Search YouTube channels by name/topic. Returns subscriber counts, video counts, country. Requires YOUTUBE_API_KEY. |
| youtube_get_channel_infoA | Detailed channel metadata: subscribers, views, videos, country, keywords. Requires YOUTUBE_API_KEY. |
| youtube_get_video_infoA | Detailed metadata for a YouTube video: title, duration, views, channel, description, tags. |
| youtube_get_trendingA | List up to |
| youtube_get_channel_videosA | List up to |
| youtube_get_playlistA | List up to |
| youtube_get_transcriptA | Transcript/subtitles of a YouTube video. Uses the original/default language; manual > ASR within that language. |
| youtube_get_frameA | Extract one ephemeral JPEG near an integer-millisecond timestamp. Returns metadata plus MCP ImageContent; accuracy is best-effort at a decoded frame boundary. |
| youtube_get_available_languagesA | Available subtitle languages for a video. Shows manual vs auto-generated. |
| youtube_get_commentsA | Retrieve up to |
| corpus_createA | Create a named corpus for semantic search over transcripts. Each corpus uses a fixed embedding model. |
| corpus_addA | Fetch a video's transcript, chunk it, and store local embeddings in an existing corpus. Use this after |
| corpus_searchA | Semantic search within a corpus. Deduplicates overlapping windows, limits source domination, and returns titles plus timestamp URLs. |
| corpus_listA | List all available corpora with chunk and video counts. |
| corpus_deleteA | Delete a corpus and all its chunks/vectors permanently. |
| tube_bridge_helpA | Get tube-bridge documentation: available tools, architecture, known limitations, API key setup. |
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 17 tools
Every tool addresses a distinct resource or action: searching channels vs. videos, fetching channel metadata vs. channel uploads, video metadata vs. transcript vs. comments vs. frames, and clear corpus operations. Even similar-looking tools like youtube_get_channel_info and youtube_get_channel_videos are unambiguous due to explicit descriptions.
Most tools follow a predictable pattern: youtube_<verb>_<resource> or corpus_<verb>. Minor deviations include youtube_get_trending (no resource noun) and tube_bridge_help (namespace mismatch), but the overall structure remains readable and consistent.
With 17 tools covering YouTube data retrieval, transcript processing, and semantic corpus management, the count is slightly high but justified by the broad scope. Each tool has a clear purpose, and the split between YouTube-facing and corpus-facing tools keeps the set manageable.
The tool set covers the full YouTube read-only surface: search, channel/video/playlist metadata, transcripts, frames, languages, comments, and trending. Corpus tools provide create/add/search/list/delete, and force_reembed covers updates. The help tool fills documentation gaps, so no critical operations are missing.