Prompt Go MCP
Smart AI workflow for Cursor teams with intelligent prompt routing, real-time cost optimization, and team analytics.
README
🎯 Prompt Go — Smart AI Workflow for Cursor Teams
Prompt smarter, spend less, work faster.
Transform your team's AI workflow with intelligent routing, real-time cost optimization, and adaptive learning. Prompt Go automatically routes each prompt to the most effective channel while providing actionable insights to reduce costs by 25-40%.
✨ What Makes It Special for Cursor Teams
🧠 Invisible Intelligence
- Zero-friction setup - Works seamlessly in Cursor with one command
- Smart routing - Automatically suggests web/agent/ask/direct based on prompt analysis
- Visual indicators - Subtle UI hints show routing confidence without interrupting flow
- Adaptive learning - Gets smarter from your team's usage patterns
💰 Proactive Cost Management
- Real-time budget tracking with smart alerts before overruns
- Automatic downgrades when approaching limits (soft enforcement)
- Cost predictions based on current usage trends
- Team efficiency scoring - see who's optimizing best
📊 Team Insights Dashboard
- Beautiful analytics at
http://localhost:8000/insights/team/your-team - Savings tracking - see exactly how much smart routing saves
- Weekly recommendations - auto-generated Cursor rules for your team
- Performance benchmarking across team members
🔒 Privacy-First Design
- 100% local processing - no data leaves your infrastructure
- Prompt hashing - content never stored, only patterns analyzed
- Team isolation - each org has separate database and config
🚀 Quick Start for Cursor Teams
Automated Setup (Recommended - 2 minutes)
git clone https://github.com/rahulraonatarajan/prompt-go-mcp.git
cd prompt-go-mcp
python setup-cursor-team.py --org "Your Team Name" --budget 500
That's it! The script will:
- ✅ Install dependencies and setup database
- ⚙️ Configure Cursor MCP settings automatically
- 📋 Create team-specific policy configuration
- 🧪 Test the integration
Manual Setup (if needed)
python -m venv .venv && . .venv/bin/activate
pip install -e .
cp .env.example .env
Add to Cursor settings.json:
{
"mcpServers": {
"prompt-go": {
"command": "python",
"args": ["-m", "apps.mcp_server"],
"cwd": "/absolute/path/to/prompt-go-mcp",
"env": {
"DATABASE_URL": "sqlite+aiosqlite:///./promptgo_yourteam.db",
"PG_ORG": "Your Team Name",
"PG_ENABLE_LEARNING": "true",
"PG_BUDGET_MODE": "soft"
}
}
}
}
📊 See It In Action
After setup, try these prompts in Cursor:
"What's the latest in React 19?"→ 🌐 Web suggested"Implement OAuth flow for our app"→ 🤖 Agent mode"Best practices for..."→ 💬 Ask for clarification"Explain useState hook"→ ⚡ Direct answer
Visit your team dashboard: http://localhost:8000/insights/team/your-team-name
🎯 Complete Documentation
📖 Cursor Team Setup Guide - Comprehensive setup and configuration
🔧 Integration Guide - Technical details and troubleshooting
📊 Dashboard: Start with python -m apps.http_dashboard then visit localhost:8000
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。