Othocs/Mambo
If you are the rightful owner of Mambo and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Mambo is an MCP server designed for Mistral’s Le Chat, focusing on AI-driven audits to identify and flag UX and design issues on websites that may negatively impact conversion rates.
🎭 Mambo
AI-driven UX audit agent that detects conversion-killing issues traditional tools miss
Mambo is an MCP server for Mistral's Le Chat that uses AI to analyze websites and identify subtle UX/design issues that hurt conversion rates. Unlike traditional tools like Lighthouse that focus on technical metrics, Mambo understands user psychology and business impact.
🎯 What Mambo Does
- UX Issues: Poor CTA visibility, confusing navigation, bad form design
- Conversion Blockers: Missing trust signals, unclear pricing, checkout friction
- Accessibility: WCAG violations, keyboard navigation issues
- Performance: Layout shifts, slow loading that impacts user experience
- Visual Design: Poor contrast, hierarchy problems, readability issues
🚀 Quick Start
Prerequisites
- Python 3.10+
- uv package manager (install guide)
- Mistral API key (get one here)
Installation
- Clone and setup the project:
git clone <your-repo-url>
cd Mambo
uv sync
- Install Playwright browsers:
uv run python scripts/setup_playwright.py
- Set your Mistral API key:
export MISTRAL_API_KEY="your-api-key-here"
Running Mambo
Start the FastMCP server:
uv run python src/mambo/server/fastmcp_server.py
🔧 Configuration for Le Chat
Add Mambo to your Claude Desktop configuration:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"mambo": {
"command": "uv",
"args": ["run", "python", "src/mambo/server/fastmcp_server.py"],
"cwd": "/path/to/your/Mambo/project",
"env": {
"MISTRAL_API_KEY": "your-actual-mistral-api-key-here"
}
}
}
}
⚠️ Important: You must include the env section with your Mistral API key, as MCP servers run in isolated environments and don't inherit shell environment variables.
📖 Usage
Once configured, you can use Mambo in Le Chat:
Basic Audit
Audit this website for UX issues: https://example.com
Mobile Audit
Run a mobile audit on https://shop.com/checkout
Quick Check
Do a quick UX check on https://landing-page.com
🛠️ Available Tools
| Tool | Description | Parameters |
|---|---|---|
audit_url | Comprehensive UX audit | url, device (desktop/mobile/tablet), wait_until |
quick_audit | Fast audit focusing on critical issues | url |
get_artifact | Retrieve screenshots or DOM snapshots | artifact_id |
📊 Sample Report
{
"success": true,
"quick_stats": {
"score": 62,
"critical_issues": 2,
"high_issues": 4,
"total_issues": 12
},
"top_issues": [
{
"title": "CTA contrast too low",
"severity": "high",
"category": "ux",
"why_it_hurts": "Primary action is hard to perceive; users may miss next step"
}
],
"summary": "Found 6 conversion-impacting issues. Primary CTA has poor contrast and sticky header overlaps form fields on mobile."
}
🏗️ Architecture
Le Chat → Mambo MCP Server → Mistral AI ↘
↗ → Analysis
Playwright → Browser
- Mistral AI: Intelligent analysis and decision making
- Playwright: Browser automation and data collection
- FastMCP: Simple MCP server implementation
- Le Chat: User interface and conversation
🛣️ Roadmap
v1.0 (Current)
- ✅ Single page audits
- ✅ Mobile/desktop analysis
- ✅ AI-powered issue detection
- ✅ FastMCP integration
v2.0 (Planned)
- 🔄 User flow analysis (multi-step journeys)
- 🔄 A/B test recommendations
- 🔄 Competitive analysis
- 🔄 Integration with analytics tools
🧪 Development
Project Structure
Mambo/
├── src/mambo/
│ ├── agent/ # Core AI agent logic
│ ├── models/ # Pydantic schemas
│ ├── server/ # MCP server
│ └── analyzers/ # Analysis modules
├── scripts/ # Setup scripts
└── tests/ # Test suite
Running Tests
uv run pytest
Code Quality
uv run ruff check --fix # Linting
uv run ruff format # Formatting
🤝 Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Make your changes and add tests
- Run quality checks:
uv run ruff check && uv run pytest - Commit using conventional commits:
git commit -m "feat: add amazing feature" - Push and create a Pull Request
📝 License
This project is licensed under the MIT License - see the file for details.
🙋♀️ Support
- 🐛 Bug reports: GitHub Issues
- 💬 Questions: GitHub Discussions
- 📧 Email: your-email@example.com
Built with ❤️ for better web experiences