Prompt Go MCP
Smart AI workflow for Cursor teams with intelligent prompt routing, real-time cost optimization, and team analytics.
README
๐ฏ Prompt Go โ 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%.
โจ What Makes It Special for Cursor Teams
๐ง 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
๐ฐ 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
๐ 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
๐ 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
๐ 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:
- โ Install dependencies and setup database
- โ๏ธ Configure Cursor MCP settings automatically
- ๐ Create team-specific policy configuration
- ๐งช 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"
}
}
}
}
๐ See It In Action
After setup, try these prompts in Cursor:
"What's the latest in React 19?"โ ๐ Web suggested"Implement OAuth flow for our app"โ ๐ค Agent mode"Best practices for..."โ ๐ฌ Ask for clarification"Explain useState hook"โ โก Direct answer
Visit your team dashboard: http://localhost:8000/insights/team/your-team-name
๐ฏ Complete Documentation
๐ Cursor Team Setup Guide - Comprehensive setup and configuration
๐ง Integration Guide - Technical details and troubleshooting
๐ Dashboard: Start with python -m apps.http_dashboard then visit localhost:8000
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.