tube-bridge
Self-hosted YouTube research for AI agents.
Search videos and channels, read transcripts and comments, extract timestamped frames, and build private semantic-search corpora — through 17 MCP tools.
Power your agent
คำสั่งของผู้เผยแพร่เอง ไม่ใช่เอนด์พอยต์ของ PlugMCP
Host a copy with our keys and logs.
uvx tube-bridge==1.1.7Claude Code ไม่มีลิงก์ติดตั้งสำหรับคำสั่งแบบโลคัล ให้คัดลอกคำสั่งด้านล่างแล้วรันในเทอร์มินัล
YOUTUBE_API_KEY=<secret> TUBE_BRIDGE_PROXY=<secret> TUBE_BRIDGE_CACHE=<value> claude mcp add io.github.thewhitewater-tube-bridge -- uvx tube-bridge==1.1.7รันในเทอร์มินัล
{ "mcpServers": { "io.github.thewhitewater-tube-bridge": { "command": "uvx", "args": [ "tube-bridge==1.1.7" ], "env": { "YOUTUBE_API_KEY": "<secret>", "TUBE_BRIDGE_PROXY": "<secret>", "TUBE_BRIDGE_CACHE": "<value>" } } }}claude_desktop_config.json
URL แบบรีโมตหรือคำสั่งบนเครื่องของคุณ? การติดตั้งสองแบบต่างกันอย่างไร
รันบน PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
เปิดจากผู้เผยแพร่
Self-hosted YouTube research for AI agents.
Search videos and channels, read transcripts and comments, extract timestamped frames, and build private semantic-search corpora — through 17 MCP tools.
YouTube MCP server for search, transcripts, frames, comments, channels, and local semantic corpora.
Thanks to everyone already using tube-bridge. If it saves you time, consider starring the repository — it helps others discover the project and signals that publishing more work like this is worthwhile.
The simplest setup uses uvx, which runs the published PyPI package in an isolated environment:
uvx tube-bridge
Normally your MCP client launches that command for you. Choose your client below.
[!NOTE] tube-bridge requires Python 3.12 or newer. An API key is optional.
ffmpegis needed only foryoutube_get_frame, and the first embedding operation may download the local model.
Open Settings → Developer → Edit Config and add:
{
"mcpServers": {
"tube-bridge": {
"command": "uvx",
"args": ["tube-bridge"]
}
}
}
Restart Claude Desktop after saving the configuration.
claude mcp add --scope user tube-bridge -- uvx tube-bridge
Create .cursor/mcp.json in your project, or add the server to your user-level MCP configuration:
{
"mcpServers": {
"tube-bridge": {
"command": "uvx",
"args": ["tube-bridge"]
}
}
}
Create .vscode/mcp.json:
{
"servers": {
"tube-bridge": {
"type": "stdio",
"command": "uvx",
"args": ["tube-bridge"]
}
}
}
codex mcp add tube-bridge -- uvx tube-bridge
Pi can load the package-relative adapter and the canonical tube-bridge-research skill from the same Git source:
python3 -m pip install tube-bridge==1.1.6
pi install git:github.com/TheWhiteWater/[email protected]
pi list
This registers one status tool plus all 17 MCP tools with the tube_bridge_ prefix. The adapter reads the existing plugin.json and mcp.json, launches only the local stdio runtime, preserves bounded text and image content, and forwards only an allowlisted child-process environment.
The Pi package manager installs the Node adapter dependency but does not install Python or ffmpeg. Ensure the python3 visible to Pi is Python 3.12+ with the tube-bridge dependencies installed; install ffmpeg separately to use youtube_get_frame. By default, Pi-managed state lives under the platform data directory; set TUBE_BRIDGE_PI_DATA to move that root. An explicit TUBE_BRIDGE_CACHE still takes precedence for the runtime databases. The optional live frame gate is /tube-bridge-selftest frame.
Remove the package with:
pi remove git:github.com/TheWhiteWater/[email protected]
If a desktop client cannot find uvx, replace "uvx" with the absolute path returned by which uvx on macOS/Linux or where.exe uvx on Windows.
Ask your agent:
Search YouTube for recent videos about local-first AI agents. Read the transcript of the strongest result, add it to a corpus named
local-agents, find the section discussing memory, return the timestamped source link, and extract a frame from that moment.
The agent can complete that request with this tool sequence:
youtube_search(query="local-first AI agents", order="date")
youtube_get_transcript(url="https://www.youtube.com/watch?v=VIDEO_ID", with_timestamps=true)
corpus_create(corpus_id="local-agents", label="Local-first AI Agents")
corpus_add(corpus_id="local-agents", url="https://www.youtube.com/watch?v=VIDEO_ID")
corpus_search(corpus_id="local-agents", query="memory architecture")
youtube_get_frame(url="https://www.youtube.com/watch?v=VIDEO_ID", timestamp_ms=FOUND_TIME_MS)
Add more videos with corpus_add, then use corpus_search to search across all of their transcripts at once.
No means no YouTube Data API key is needed; network access to YouTube may still be required. Search, video information, and trending work without a key through yt-dlp and upgrade to Data API v3 when a key is configured.
A YouTube Data API v3 key unlocks comments, channel search, and channel details. It also improves search, video information, and trending reliability.
Create a key in Google Cloud Console, enable YouTube Data API v3, and expose it to the process launching tube-bridge:
export YOUTUBE_API_KEY="your-key"
Keep keys out of committed MCP configuration files. Use your client's secret/environment support where available.
Corpus storage and embedding inference are local to the machine running tube-bridge.
~/.tube_bridge/corpus.dbSet TUBE_BRIDGE_CACHE to move both corpus and cache databases:
export TUBE_BRIDGE_CACHE="/path/to/tube-bridge-data"
The embedding model may be downloaded on first use. After the assets are available, embedding inference does not require an external model API.
youtube_get_frame requires ffmpeg on PATH; the Docker image already includes it.
Each call downloads a short temporary section around timestamp_ms, returns one bounded JPEG as MCP ImageContent, and removes the temporary media before returning. It does not create a frame or clip library.
pip install tube-bridge
tube-bridge # stdio
tube-bridge --http # Streamable HTTP on port 8080
docker run --rm -p 8080:8080 ghcr.io/thewhitewater/tube-bridge:latest
The health endpoint is http://localhost:8080/health; the Streamable HTTP endpoint is http://localhost:8080/mcp.
Registry name: io.github.TheWhiteWater/tube-bridge
Registry-aware clients can install the PyPI distribution with uvx and launch the stdio server without a hosted intermediary.
For an HTTP instance you operate:
{
"mcpServers": {
"tube-bridge": {
"type": "http",
"url": "https://your-host.example/mcp"
}
}
}
Protect remote MCP routes by setting a server-side Bearer key:
export TUBE_BRIDGE_AUTH_KEY="choose-a-long-random-value"
tube-bridge --http
Then configure a header-capable client:
{
"mcpServers": {
"tube-bridge": {
"type": "http",
"url": "https://your-host.example/mcp",
"headers": {
"Authorization": "Bearer <your-key>"
}
}
}
}
/health remains public. /mcp, /sse, and /messages require the Bearer key when TUBE_BRIDGE_AUTH_KEY is set. Legacy SSE is available at /sse for clients that still need it.
MCP client
│
├── discovery and metadata ── Data API v3 (when configured)
│ └─ yt-dlp fallback
├── transcripts ───────────── youtube-transcript-api
├── timestamped frames ────── yt-dlp + ffmpeg → ephemeral JPEG
└── semantic corpus ───────── SQLite + sqlite-vec + local fastembed
/mcp for self-hosted remote use;code, source, and retryable fields;GitHub Releases include tube-bridge-agent-plugin-<version>.zip, containing:
tube-bridge-research skill;Agent Plugins v1 does not standardize dependency installation. Install Python 3.12+, ffmpeg, and the package dependencies in the environment used by the plugin host. The bundle contains no credentials.
If YouTube blocks requests from your network, set TUBE_BRIDGE_PROXY. Keep proxy credentials in environment variables rather than committed configuration.
git clone https://github.com/TheWhiteWater/tube-bridge.git
cd tube-bridge
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements-release.txt
pip install --no-deps -e .
pip install pytest pytest-asyncio pytest-mock build twine
python -m pytest tests -q
python test_tools.py is an optional live YouTube smoke test. The deterministic test suite does not call YouTube.
See CONTRIBUTING.md to contribute. Security reports should follow SECURITY.md.
MIT — see LICENSE.
YouTube MCP server for search, transcripts, frames, comments, channels, and local semantic corpora.
{ "mcpServers": { "io.github.thewhitewater-tube-bridge": { "command": "uvx", "args": [ "tube-bridge==1.1.7" ], "env": { "YOUTUBE_API_KEY": "<secret>", "TUBE_BRIDGE_PROXY": "<secret>", "TUBE_BRIDGE_CACHE": "<value>" } } }}เครื่องมือ
ยังไม่มีรายการเครื่องมือ เซิร์ฟเวอร์แบบรีโมตจะได้รายการหลังการตรวจสอบสถานะครั้งแรก
FAQ
คัดลอกคอนฟิก stdio สำหรับ Cursor, Claude Desktop, Claude Code หรือ VS Code ได้ในหน้านี้ คอนฟิกนี้ใช้การติดตั้งของผู้เผยแพร่ ไม่ใช่พร็อกซีของ PlugMCP
ผู้เผยแพร่ระบุตัวแปรสภาพแวดล้อมเหล่านี้: YOUTUBE_API_KEY, TUBE_BRIDGE_PROXY, TUBE_BRIDGE_CACHE
Tube Bridge ทำงานแบบโลคัลผ่าน stdio
ตรวจสอบล่าสุดเมื่อ 2026-11-11 YouTube MCP server for search, transcripts, frames, comments, channels, and local semantic corpora.