MCP Mortgage Server

🚀 Mortgage Comparison Platform (MCP) Server

A FastAPI-based server that provides mortgage document parsing and comparison tools via standard APIs. This server is designed to be easily integrated with various AI frameworks, including CrewAI, AutoGen, and LangChain.

Currently, a simple "Hello" tool has been implemented as a proof of concept. The upcoming version will introduce mortgage document parsing functionality.

🚀 Quick Start

1. Clone the repository:

   git clone https://github.com/confersolutions/mcp-mortgage-server.git
   cd mcp-mortgage-server
   

✨ Features

• A FastAPI server with production-ready features:
  • API key authentication
  • Rate limit support
  • CORS middleware configuration
• Integration with AI agent frameworks:
  • CrewAI
  • AutoGen
  • LangChain
• An extensible architecture for adding mortgage parsing tools
• Open source for transparency and community contributions

📦 Installation

1. Clone the repository to your local machine:

   git clone https://github.com/yourusername/mcp-server.git
   cd mcp-server
   

2. Create a virtual environment and install dependencies:

   python -m venv venv
   source venv/bin/activate  # Use `venv\Scripts\activate` on Windows
   pip install -r requirements.txt
   

3. Configure environment variables. Edit the .env file:

   API_KEY=your_api_key_here
   RATE_LIMIT_PER_MINUTE=120
   ALLOWED_ORIGINS=http://localhost:3000,http://localhost:8000
   

4. Start the server:

   uvicorn main:app --reload
   

💻 Usage Examples

Basic Usage

After starting the server, it will be available at http://localhost:8000.

Advanced Usage

API Endpoints

• /health

  • Method: GET
  • Description: Check the server status.
  • Response: { "status": "ok" }

• /hello/{name}

  • Method: GET
  • Description: Return a greeting message.
  • Path Parameter: name (string)
  • Example Response: "Hello, World!"

Framework Integration Examples

CrewAI Integration

Add the following code to main.py:

from crewai import Crew
crew = Crew("your_api_key")
@app.get("/generate")
async def generate(context: str):
    return await crew.generate(context)

AutoGen Integration

Add the following code to main.py:

from autogen import Agent
agent = Agent()
@app.get("/analyze")
async def analyze(text: str):
    return agent.analyze(text)

🔧 Technical Details

Status

This is a beta version (v0.1.0), offering the following features:

• Core server infrastructure with security features
• Framework integration examples with CrewAI, AutoGen, and LangChain
• A basic "Hello" tool for testing framework integration

Upcoming versions will include mortgage document parsing and comparison tools.

Roadmap

• ✅ Core server infrastructure with security and rate limiting
• ✅ Framework integration with CrewAI, AutoGen, and LangChain
• ✅ Basic tool implementation ("Hello" endpoint)
• 🚧 Parse Loan Estimates (LE) into MISMO format
• 🚧 Development of mortgage comparison tools

Rate Limiting

The server uses slowapi to implement rate limiting, with a default setting of 120 requests per minute per IP. It can be configured via the RATE_LIMIT_PER_MINUTE environment variable.

Security

• All endpoints require API key authentication, except /health.
• CORS configuration allows specific origins (set via the ALLOWED_ORIGINS environment variable).
• All exceptions are caught and appropriate error messages are returned.

🤝 Contribution

Feel free to submit issues or code improvements.

📄 About

This project is maintained by Confer Solutions. For help or support, please contact info@confersolutions.ai.

📄 License

This project is under the MIT License - see the LICENSE file for details.