Tube Search MCP Server

MCP server for Archivarix Tube Search — search archived YouTube videos via AI assistants

Local serverstdio

What is the Tube Search MCP MCP server?

MCP server for Archivarix Tube Search — search archived YouTube videos via AI assistants. Exposed over MCP by the tube search mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

Its toolset

Everything the assistant can do here goes through one of these:

  • 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
  • Cursor — The Cursor tool exposed by this server

Adding it to your client

tube-search-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Configuration

You will need 2 environment variables: TUBE_API_KEY, TUBE_MCP_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Tube Search MCP's toolset — search_channel, search_videos, get_video and 7 more — is a fair guide to whether it matches your workflow. It is maintained by archivarix-com; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Tube Search MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the tube search mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
search_channelFind all archived videos from a YouTube channel
search_videosFull-text search across video titles and descriptions
get_videoGet metadata for a specific video by ID
get_subtitlesGet transcript as readable plain text
get_summaryGet AI-generated video summary
generate_summaryGenerate a new AI summary for a video
browse_summariesBrowse summaries by tag, channel, or language
get_video_status_historyView status change history of a video
get_usageCheck your current API usage and limits
CursorThe Cursor tool exposed by this server.

How to install the Tube Search MCP MCP server

{
  "mcpServers": {
    "tube-search": {
      "command": "npx",
      "args": ["-y", "tube-search-mcp"],
      "env": {
        "TUBE_API_KEY": "tsk_YOUR_KEY"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
TUBE_API_KEYCredential the server authenticates with.Yes
TUBE_MCP_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Tube Search MCP to search channel.
  • Use Tube Search MCP to search videos.
  • Use Tube Search MCP to get video.

Frequently asked questions

It connects Tube Search MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (search_channel, search_videos, get_video, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Tube Search MCP directly.