YouTube Browser Control

YouTube Browser Control

An MCP server for YouTube automation using Playwright and Gemini AI agent. Enables browser control for YouTube operations like searching, playing videos, skipping ads, and managing playback through natural language commands.

Category
Visit Server

README

YouTube Browser Control - MCP Server

YouTube automation MCP server using Playwright + Gemini agent (no Selenium).

Cài đặt

1. Cài Python

  • Tải Python 3.8+ từ: https://www.python.org/downloads/
  • Khi cài, tick chọn "Add Python to PATH"

2. Cài thư viện

pip install -r requirements.txt

3. Cấu hình API key + Endpoint

  • Tạo file .env với nội dung:
GEMINI_API_KEY=YOUR_GEMINI_API_KEY
MCP_ENDPOINT=wss://api.xiaozhi.me/mcp/?token=YOUR_TOKEN_HERE
# Tùy chọn: tắt tự kết nối lại khi WebSocket rớt (mặc định bật)
# MCP_WS_RECONNECT=false
  • Truy cập https://xiaozhi.me để lấy WebSocket token cho MCP_ENDPOINT.
  • Nếu log vẫn báo đóng kết nối mã 1006 sau khi cập nhật bridge (heartbeat + reconnect), broker hoặc mạng có thể đang timeout trong lúc chờ tools/call lâu — kiểm tra giới hạn thời gian / chính sách phía xiaozhi hoặc proxy cục bộ.

4. Chạy chương trình

python client.py

Tools có sẵn

  • open_youtube - Mở YouTube
  • search_video - Tìm kiếm video
  • play_first_video - Phát video đầu tiên
  • search_and_play - Prompt automation: mở YouTube, tìm query, chọn video phù hợp, phát video
  • search_and_play_with_agent - Alias của search_and_play
  • skip_ad - Bỏ qua quảng cáo
  • toggle_fullscreen - Bật/tắt fullscreen
  • get_current_url - Lấy URL hiện tại
  • close_browser - Đóng trình duyệt

Chế độ chạy

# WebSocket (mặc định)
python client.py

# Debug mode
python client.py --debug

# Stdio mode
python client.py stdio

Lưu ý: Server giữ browser session để bạn có thể gọi nhiều tool liên tiếp (search_video -> play_first_video -> skip_ad). "# mcp"

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured