Ocular Audio Mcp

Overview

Ocular Audio Mcp is a Model Context Protocol server that extracts video transcripts, screenshots, and OCR text from YouTube and web videos. Any MCP-compatible AI assistant can invoke its tools directly, letting models decide when to use them during conversations or agent workflows.

The server runs locally via the npm package ocular-audio-mcp, which communicates over stdio on your machine. No authentication is required. Install it with npx -y ocular-audio-mcp. The latest release is v1.1.2, published under the MIT license with source code at RayAKaan/OcularAudio-MCP on GitHub.

Ocular Audio Mcp appears in the Development category on mcp.site and integrates with all major MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, claim the listing to verify ownership and keep information up to date.

Installation

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