Twitter Video Downloader MCP Server for AI Agents

The Model Context Protocol (MCP) is an open standard that lets AI agents call external tools. This MCP server gives an agent the ability to pull media and direct download links from public Twitter/X posts, so you can ask it in plain language to fetch a video.

Short answer: point your MCP client at https://download-twitter-video.drummerduck.com/api/mcp. It exposes two tools — extract_twitter_video and get_tweet_info.

The endpoint

The server speaks Streamable HTTP at:

https://download-twitter-video.drummerduck.com/api/mcp

Tools

• extract_twitter_video({ url }) — returns the full media list plus direct download URLs for each quality variant.
• get_tweet_info({ url }) — returns metadata only (author, text, timestamp, media types) without the download URLs.

Both take a single url argument pointing at a tweet.

Client configuration

For clients that support remote MCP servers over a URL (Claude Desktop, Cursor, and similar), add:

{
  "mcpServers": {
    "twitter-video": {
      "url": "https://download-twitter-video.drummerduck.com/api/mcp"
    }
  }
}

For stdio-only clients, bridge to the remote server with mcp-remote:

{
  "mcpServers": {
    "twitter-video": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://download-twitter-video.drummerduck.com/api/mcp"
      ]
    }
  }
}

Restart the client after saving so it picks up the new server.

Example prompts

Once the server is connected, you can ask an agent things like:

• "Extract the video from https://x.com/user/status/1234567890 and give me the 1080p download link."
• "What's in this tweet — who posted it and does it have a video or a GIF? https://x.com/user/status/1234567890"
• "Grab the highest-quality MP4 from this tweet and save it to my downloads folder: https://x.com/user/status/1234567890"

The agent calls get_tweet_info for metadata questions and extract_twitter_video when it needs the actual media and download URLs.

How it relates to the REST API

The MCP server wraps the same extraction engine as the REST API. Use MCP when an AI agent should call the tool conversationally; use the REST API for scripts and backend integrations. Non-developers can just use the web downloader or follow the how-to guide.

Frequently asked questions

What is MCP?

The Model Context Protocol is an open standard for connecting AI agents to external tools and data sources through a consistent interface.

Which clients work?

Any MCP-capable client. URL-based clients connect directly; stdio-only clients use the mcp-remote bridge shown above.

Does it return direct download links?

Yes. extract_twitter_video returns each variant's direct URL, including 1080p Full HD when available.

Can it handle GIFs and images?

Yes — GIFs come back as silent MP4s (see the GIF guide) and images are returned too.

Only download public content you have the right to use, and respect copyright.