Archivarix Tube Search
@Archivarix-com
About Archivarix Tube Search
MCP server for Archivarix Tube Search — search archived YouTube videos including deleted content. Channel discovery, full-text search, video metadata, transcripts, and AI-generated summaries via the Wayback Machine. 1.5B+ videos indexed since 2005.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"tube-search": {
"command": "npx",
"args": [
"-y",
"tube-search-mcp"
],
"env": {
"TUBE_API_KEY": "tsk_YOUR_KEY"
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Archivarix Tube Search?
Archivarix Tube Search is a search engine for archived YouTube videos, including deleted, removed, and region-blocked content. The MCP server wraps the public API so AI agents (Claude Desktop, Claude Code, VS Code, Cursor) can search 1.5+ billion videos indexed since 2005.
How to use Archivarix Tube Search?
Install with npx tube-search-mcp — works on macOS / Linux / Windows. Requires Node.js 18+ and a free API key from tube.archivarix.net (Profile → API Keys). Once configured, AI agents can invoke 9 tools and access 5 resources and 3 prompts.
Key features of Archivarix Tube Search
- Search 1.5+ billion archived YouTube videos since 2005
- Retrieve video metadata, captions, and AI-generated summaries
- Access full audio transcripts from surviving archived audio
- Discover channels across legacy username/handle/@-tag forms
- Reconstruct playable URLs to archived video files when available
Use cases of Archivarix Tube Search
- Finding a deleted YouTube video by title or description
- Retrieving original captions or subtitles from an archived video
- Generating AI summaries of archived video content on demand
- Browsing channel video history after channel removal
- Checking video status history and current API usage
FAQ from Archivarix Tube Search
What data sources are used?
Internet Archive Wayback Machine (CDX + HEAD-spread discovery), Common Crawl, YouTube Metadata 2019 dump, and live yt-dlp probes for surviving content.
What tools are available?
Nine tools: search_channel, search_videos, get_video, get_subtitles, get_summary, generate_summary, browse_summaries, get_video_status_history, and get_usage.
Is there a free tier?
Yes: a free tier covers anonymous and registered users. Paid tiers (Plus, MCP+API) unlock higher rate limits, on-demand AI summaries, and audio transcription.
What are the runtime requirements?
Node.js 18+ and a free API key from tube.archivarix.net.
Does it support resources and prompts?
Yes: 5 resources (tube://video/{id}, tube://channel/{id}, tube://subtitles/{id}, tube://summary/{id}, tube://tags) and 3 prompts (research_video, channel_overview, find_deleted).
Frequently asked questions
What data sources are used?
Internet Archive Wayback Machine (CDX + HEAD-spread discovery), Common Crawl, YouTube Metadata 2019 dump, and live yt-dlp probes for surviving content.
What tools are available?
Nine tools: search_channel, search_videos, get_video, get_subtitles, get_summary, generate_summary, browse_summaries, get_video_status_history, and get_usage.
Is there a free tier?
Yes: a free tier covers anonymous and registered users. Paid tiers (Plus, MCP+API) unlock higher rate limits, on-demand AI summaries, and audio transcription.
What are the runtime requirements?
Node.js 18+ and a free API key from tube.archivarix.net.
Does it support resources and prompts?
Yes: 5 resources (tube://video/{id}, tube://channel/{id}, tube://subtitles/{id}, tube://summary/{id}, tube://tags) and 3 prompts (research_video, channel_overview, find_deleted).
Basic information
More Search MCP servers
Serper Search and Scrape MCP Server
marcopesaniSerper MCP Server supporting search and webpage scraping
SearXNG MCP Server
ihor-sokoliukPrivate web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client
Brave Search
modelcontextprotocolModel Context Protocol Servers
Wigolo
KnockOutEZThe go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
DuckDuckGo Search MCP Server
nickclydeA Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
Comments