Spring Ai Mcp

by rifatcakir

359 downloads
Not rated
GitHub

About

AI-powered chat assistant for banking microservices using Spring AI and Model Context Protocol (MCP). Interact with your microservices through natural language chat, view accounts, personal details, and transactions—all in one unified interface.

Details

Author
rifatcakir
Downloads
359
Categories
AI

- Natural language processing for service interactions
- Unified chat interface for all microservices
- Real-time communication with multiple services
- Seamless integration of new microservices

Clone the repository, build the project with mvn clean install, then start each microservice and the chat client in separate terminals using mvn spring-boot:run -pl <module-name>. Access the chat client application, type requests in natural language, and the system will parse, route, and execute the requested operations.

Spring AI MCP (Model Context Protocol)

This project demonstrates how to implement a chat-based interface for communicating with microservices using Spring AI and MCP (Model Context Protocol). The system allows users to interact with various microservices through natural language chat, making it easier to perform operations across different services by providing contextual understanding and model-driven interactions.

Project Structure

The project consists of the following components:

- chat-client: A Spring Boot application that provides the chat interface for users to interact with microservices
- person-mcp-service: Microservice for managing person-related operations
- account-mcp-service: Microservice for handling account-related operations
- transaction-mcp-service: Microservice for processing transaction-related operations

Prerequisites

- Java 21
- Maven 3.8+
- Spring Boot 3.5.0
- Spring AI 1.0.0

Getting Started

1. Clone the repository:

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

2. Build the project:

mvn clean install

3. Start the services:
```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.