Video Reader MCP

Overview

Video Reader MCP is a Model Context Protocol server that analyzes videos evidence-first, generating timeline documents with ffprobe streams and subtitle cues. It lets AI assistants work directly with video metadata and timing information as callable tools instead of requiring manual data extraction between applications.

The server runs locally via the npm package @sylphx/video-reader-mcp, installed with npx -y @sylphx/video-reader-mcp. It requires no authentication and communicates over stdio on your machine. Version v0.1.0 is available now under the MIT license, with source code at SylphxAI/video-reader-mcp on GitHub.

Video Reader MCP belongs in the Development category on mcp.site and works with any MCP client including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim this listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "video_reader_mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@sylphx/video-reader-mcp"
      ]
    }
  }
}