Spring MCP Bridge

Spring MCP Bridge is a tool that automatically converts REST endpoints from Spring Boot applications into an MCP (Message Conversation Protocol) server, allowing AI assistants like Claude, Cursor, and other MCP-compatible tools to directly interact with your APIs.

*It does not currently include authentication. If your Spring Boot API requires authentication, you will need to modify the handler code to include the appropriate headers or tokens.

📖 Overview

Integrating existing APIs with AI assistants typically requires manual coding or complex configuration. Spring MCP Bridge eliminates this complexity by automatically scanning your Spring Boot project and generating a ready-to-use MCP server.

✨ Features

• Automatic Scanning: Discovers all REST endpoints (@RestController, @GetMapping, etc.)
• Zero Configuration: No modifications needed to existing Spring Boot code
• Model Preservation: Maintains request and response models as MCP tools
• Javadoc Extraction: Uses existing documentation to enhance MCP tool descriptions
• Complete Documentation: Generates README and clear instructions for use

🚀 Installation

# Clone the repository
git clone https://github.com/brunosantos/spring-mcp-bridge.git

# Enter the directory
cd spring-mcp-bridge

🛠️ Usage

1. Scan your Spring Boot project:

python spring_boot_mcp_converter.py --project /path/to/spring-project --output ./mcp_server --name MyAPI

2. Run the generated MCP server:

cd mcp_server
pip install -r requirements.txt
python main.py

3. Connect via MCP client:
   • Configure your MCP client (Claude, Cursor, etc.) to use http://localhost:8000
   • The MCP schema will be available at http://localhost:8000/.well-known/mcp-schema.json

📋 Arguments

💻 Example

python spring_mcp_bridge.py --project ~/projects/my-spring-api --output ./mcp_server --name MyAPI

The tool will:

1. Scan the Spring Boot project for REST controllers
2. Identify model types, parameters, and return types
3. Generate a fully functional MCP server in Python/FastAPI
4. Create a compatible MCP schema that describes all endpoints

🔄 How It Works

1. Scanning: Analyzes Java source code to extract metadata from REST endpoints
2. Conversion: Converts Java types to JSON Schema types for MCP compatibility