This server connects Claude to the Archivarix Tube Search API, giving you access to over a billion archived YouTube videos dating back to 2005. You get nine tools including search_videos for full-text queries, get_video for metadata on specific IDs, get_subtitles for transcripts, and get_summary for AI-generated overviews. It also exposes search_channel to pull all archived content from a given channel and get_video_status_history to see when videos went private or got deleted. The setup is straightforward: grab an API key from tube.archivarix.net and drop it into your MCP config. Useful when you need to reference content that's no longer publicly available or track how video metadata has changed over time.
MCP server for Archivarix Tube Search — search archived YouTube videos via AI assistants.
Search over 1 billion YouTube videos indexed since 2005. Find deleted videos, metadata, thumbnails, and subtitles.
npx tube-search-mcp --api-key tsk_YOUR_KEY
Or with environment variable:
export TUBE_API_KEY=tsk_YOUR_KEY
npx tube-search-mcp
Get your API key at tube.archivarix.net (Profile → API Keys).
Add to ~/.claude/claude_desktop_config.json:
{
"mcpServers": {
"tube-search": {
"command": "npx",
"args": ["-y", "tube-search-mcp"],
"env": {
"TUBE_API_KEY": "tsk_YOUR_KEY"
}
}
}
}
Add to ~/.claude/mcp.json:
{
"mcpServers": {
"tube-search": {
"command": "npx",
"args": ["-y", "tube-search-mcp"],
"env": {
"TUBE_API_KEY": "tsk_YOUR_KEY"
}
}
}
}
Add to .vscode/mcp.json in your project:
{
"servers": {
"tube-search": {
"command": "npx",
"args": ["-y", "tube-search-mcp"],
"env": {
"TUBE_API_KEY": "tsk_YOUR_KEY"
}
}
}
}
Add to ~/.cursor/mcp.json:
{
"mcpServers": {
"tube-search": {
"command": "npx",
"args": ["-y", "tube-search-mcp"],
"env": {
"TUBE_API_KEY": "tsk_YOUR_KEY"
}
}
}
}
| Tool | Description |
|---|---|
search_channel | Find all archived videos from a YouTube channel |
search_videos | Full-text search across video titles and descriptions |
get_video | Get metadata for a specific video by ID |
get_subtitles | Get transcript as readable plain text |
get_summary | Get AI-generated video summary |
generate_summary | Generate a new AI summary for a video |
browse_summaries | Browse summaries by tag, channel, or language |
get_video_status_history | View status change history of a video |
get_usage | Check your current API usage and limits |
| URI | Description |
|---|---|
tube://video/{videoId} | Video metadata |
tube://channel/{channelId} | Channel info |
tube://subtitles/{videoId} | Transcript as plain text |
tube://summary/{videoId} | AI-generated summary |
tube://tags | Popular summary tags |
| Prompt | Description |
|---|---|
research_video | Comprehensive video analysis workflow |
channel_overview | Channel research and statistics |
find_deleted | Discover and analyze deleted videos |
| Variable | Description | Default |
|---|---|---|
TUBE_API_KEY | API key (required) | — |
TUBE_MCP_URL | Custom MCP endpoint | https://tube.archivarix.net/mcp |
This package acts as a stdio-to-HTTP proxy. It connects to the remote Archivarix Tube Search MCP server via Streamable HTTP and exposes the same tools, resources, and prompts over stdio transport for local AI clients.
AI Client ←(stdio)→ tube-search-mcp ←(HTTP)→ tube.archivarix.net/mcp
Full documentation: tube.archivarix.net/guide/mcp
MIT
TUBE_API_KEY*secretAPI key for Archivarix Tube Search. Obtain at https://tube.archivarix.net/profile (Plus tier or API tier required).
com.mcparmory/google-search
io.github.pipeworx-io/brave-search
marcopesani/mcp-server-serper
brave/brave-search-mcp-server
com.mcparmory/google-search-console
acamolese/google-search-console-mcp