vid2llm

Overview

vid2llm is a Model Context Protocol server that transforms public videos from TikTok, YouTube, Instagram, and X into readable text. It integrates directly with AI assistants as callable tools, letting your models analyze video content on demand. Each video processes through the x402 pay-per-use system, so you only pay for what you actually convert.

The server runs locally on your machine via the npm package vid2llm-mcp, installed with npx -y vid2llm-mcp. You'll need an API key to authenticate. The latest release is v0.3.0, maintained at https://vid2llm.dev.

Find vid2llm in the Development category on mcp.site. It works with Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and other MCP clients. If you maintain vid2llm, claim this listing to verify ownership and keep the information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "vid2llm": {
      "command": "npx",
      "args": [
        "-y",
        "vid2llm-mcp"
      ]
    }
  }
}