Metadata-Version: 2.4
Name: dcisionai-mcp-server
Version: 3.1.4
Summary: DcisionAI MCP Server - AI-Powered Optimization with Intent Classification & Session Persistence
Project-URL: Homepage, https://dcisionai.com
Project-URL: Repository, https://github.com/ameydhavle/dcisionai-mcp-platform
Project-URL: Issues, https://github.com/ameydhavle/dcisionai-mcp-platform/issues
Project-URL: Documentation, https://github.com/ameydhavle/dcisionai-mcp-platform/blob/main/README.md
Author-email: Amey Dhavle <amey@dcisionai.com>
License: MIT
Keywords: ai,claude,cursor,dame,evolutionary-algorithm,highs,job-shop,llm,mathematical-programming,mcp,optimization,portfolio-optimization,retail-layout,trust-score,vrp,vscode,workforce-scheduling
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Financial and Insurance Industry
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.10
Requires-Dist: aiohttp>=3.9.0
Requires-Dist: anthropic>=0.40.0
Requires-Dist: fastmcp>=2.13.0
Requires-Dist: highspy>=1.7.0
Requires-Dist: httpx>=0.27.0
Requires-Dist: numpy>=1.24.0
Requires-Dist: openai>=1.0.0
Requires-Dist: pandas>=2.0.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: scipy>=1.10.0
Requires-Dist: supabase>=2.0.0
Provides-Extra: dev
Requires-Dist: black>=23.0.0; extra == 'dev'
Requires-Dist: pytest-asyncio>=0.21.0; extra == 'dev'
Requires-Dist: pytest>=7.0.0; extra == 'dev'
Description-Content-Type: text/markdown

# DcisionAI MCP Server

**AI-Powered Optimization for Cursor, Claude Desktop & VS Code**

Solve complex optimization problems directly in your IDE using natural language. Get mathematically-verified solutions with **90%+ trust scores** in seconds.

## 🚀 Quick Start

### Installation (Zero Configuration!)

```bash
# That's it! No installation needed with uvx
```

### Configure Your IDE

**For Cursor or Claude Desktop:**

Add to your MCP config file (`~/.cursor/mcp.json` on Mac):

```json
{
  "mcpServers": {
    "dcisionai-optimization": {
      "command": "uvx",
      "args": ["dcisionai-mcp-server@latest"],
      "env": {
        "DCISIONAI_API_URL": "https://dcisionai-mcp-platform-production.up.railway.app"
      },
      "autoApprove": ["dcisionai_solve", "dcisionai_solve_with_model"]
    }
  }
}
```

### Use It!

In Cursor or Claude Desktop, just ask:

```
"Use DcisionAI to optimize my $500K portfolio concentrated in tech stocks"

"Use DcisionAI to optimize delivery routes for 20 customers"

"Use DcisionAI to optimize employee scheduling for 30 workers across 50 shifts"
```

## ✨ What Can It Do?

### 📊 Finance
- Portfolio rebalancing with risk constraints
- Trading schedule optimization  
- Asset allocation with concentration limits
- Private equity exit timing

### 🏪 Retail
- Store layout optimization (shelf space allocation)
- Inventory management
- Pricing optimization
- Supply chain optimization

### 🏭 Manufacturing
- Production scheduling
- Resource allocation
- Job shop optimization
- Workforce scheduling

### 🚚 Logistics
- Vehicle routing (VRP)
- Delivery route optimization
- Warehouse layout
- Distribution network design

## 🛠️ Tools

- **`dcisionai_solve`** - Full optimization workflow (classification, intent extraction, solving, explanation)
- **`dcisionai_solve_with_model`** - Solve using deployed models (faster for known problem types)

## 📚 Resources

- **`dcisionai://models/list`** - Available deployed models
- **`dcisionai://solvers/list`** - Available solvers (HiGHS, SCIP, DAME, OR-Tools)

## 🔧 Configuration

Set environment variables:

- `DCISIONAI_API_URL`: Backend API URL (default: `http://localhost:8000`)
- `DCISIONAI_API_KEY`: API key for authentication (optional)
- `DCISIONAI_DOMAIN_FILTER`: Domain filter (`"all"`, `"ria"`, `"pe"`, etc.)
- `DCISIONAI_LOG_LEVEL`: Logging level (`"INFO"`, `"DEBUG"`, etc.)

## 📖 Documentation

- [Full Documentation](https://github.com/ameydhavle/dcisionai-mcp-platform)
- [MCP Server Planning](https://github.com/ameydhavle/dcisionai-mcp-platform/blob/main/docs/MCP_SERVER_PLANNING.md)
- [Architecture Decision Record](https://github.com/ameydhavle/dcisionai-mcp-platform/blob/main/docs/adr/029-mcp-server-integration-architecture.md)

## 🤝 Contributing

Contributions welcome! See our [GitHub repository](https://github.com/ameydhavle/dcisionai-mcp-platform) for details.

## 📄 License

MIT License - see LICENSE file for details.

## 🔗 Links

- **Homepage**: https://dcisionai.com
- **Repository**: https://github.com/ameydhavle/dcisionai-mcp-platform
- **Issues**: https://github.com/ameydhavle/dcisionai-mcp-platform/issues

