RagMCP
A local command-based assistant that enables users to control system tools, play YouTube music, and search various websites using Playwright automation. It supports tasks ranging from media playback and browser navigation to file system operations and system power management.
README
✅ RagMCP Project Manual (Developer Guide)
🔥 1. Project Overview
RagMCP is a local command-based assistant that:
✅ Opens websites ✅ Plays YouTube songs using Playwright ✅ Controls system tools (create folder, set wallpaper, shutdown PC) ✅ Searches websites like FitGirl, Pinterest, etc.
It works using a server (ragmcp) that listens to JSON commands and performs actions.
📥 2. Download the Project
Option 1: Clone GitHub Repo
git clone https://github.com/yourusername/RagMCP.git
cd RagMCP
Option 2: Download Zip
- Click Download Zip
- Extract to
D:\MINI PROJECTS\RAGMCP
🧰 3. Setup Python Environment
3.1 Create Virtual Environment
python -m venv .venv
3.2 Activate Virtual Environment
Windows PowerShell
.\.venv\Scripts\Activate
📦 4. Install Required Packages
Run:
pip install -r requirements.txt
If requirements.txt not exist, install manually:
pip install playwright pyautogui
pip install psutil
⚠️ Playwright Browser Setup
playwright install
🚀 5. Run the Server
Start RagMCP Server
ragmcp
If command not found:
python -m ragmcp
🧩 6. How to Use RagMCP (JSON Commands)
Example format:
{"id": 1, "method": "METHOD_NAME", "params": {"param": "value"}}
🎯 7. YouTube Tool Commands
Case 1: Play Specific Song
{"id": 1, "method": "play_youtube_direct", "params": {"query": "Naa Ready song"}}
Case 2: Play Trending Music
{"id": 1, "method": "play_trending_music", "params": {}}
Case 3: Play Favourite Song
{"id": 1, "method": "play_youtube_from_favourites", "params": {"favourite": "A.R. Rahman"}}
Mood Based Music
{"id": 1, "method": "play_youtube_mood", "params": {"mood": "happy"}}
🌐 8. Web Tools Commands
Open any website
{"id": 1, "method": "open_website", "params": {"site": "google"}}
Search on Google
{"id": 1, "method": "search_google", "params": {"query": "Thalapathy aesthetic"}}
Search on FitGirl
{"id": 1, "method": "search_fitgirl", "params": {"query": "Batman Arkham City"}}
Search on Pinterest
{"id": 1, "method": "search_pinterest", "params": {"query": "Thalapathy aesthetics"}}
🖥️ 9. System Tools Commands
Create Folder
{"id": 1, "method": "create_folder", "params": {"path": "C:\\Users\\User\\Desktop\\afrah"}}
Set Wallpaper
{"id": 1, "method": "set_wallpaper", "params": {"path": "D:\\wallpapers\\image.jpg"}}
Shutdown PC
{"id": 1, "method": "shutdown_pc", "params": {}}
🧠 10. Important Notes
✔️ Always run ragmcp server first ✔️ Use Chrome-based browsers for best stability ✔️ Playwright opens browser automatically and waits until user closes it ✔️ Do not change logic without understanding it
🏁 Project Finalization
Once you run all tools and verify functionality:
✅ Save project ✅ Commit to GitHub ✅ Share with developer
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。