- Implement MCP server with async/sync support and builder pattern configuration - Add Server stdio/SSE transport layers with robust error handling - Convert McpClient and McpServer to interfaces for better extensibility - Add sampling capabilities for LLM interactions (text/image) - Implement dynamic root management and runtime tool management - Add comprehensive prompt and resource capabilities - Add support for dynamic root management (add/remove roots at runtime) Architecture Changes - Introduce registration records for tools, resources, and prompts - Improve thread safety with concurrent collections - Enhance resource template handling - Implement builder patterns for Server/Client capabilities - Add support for server capabilities and implementation info Transport Layer: - Implement SseServerTransport with SSE endpoints - Add StdioServerTransport for process-based communication - Reorganize transport packages for better organization - Improve transport error handling and shutdown processes Documentation: - Add detailed MCP reference documentation - Include architecture diagrams and API documentation - Add comprehensive test coverage for all components - Include sample projects demonstrating stdio/SSE transports BREAKING CHANGES: Transport Package Reorganization - Move StdioClientTransport to o.s.ai.mcp.client.transport - Move SseClientTransport to o.s.ai.mcp.client.transport - Move ServerParameters to o.s.ai.mcp.client.transport - StdioClientTransport.errorHandler changed to private with setter method Migration: Use setErrorHandler() method instead of direct field access API Changes - Replace static factory methods with builder pattern - Update ServerCapabilities to use builder pattern - Make StdioClientTransport.errorHandler private with setter - Replace rootsListProvider with direct root management - Remove deprecated static factory methods Resolves #27,#25,#24,#11 Related to #12
1.7 KiB
1.7 KiB
Spring AI MCP Spring
Spring Integration module for Model Control Protocol (MCP) that provides Spring-specific functionality for working with MCP clients.
Overview
The spring-ai-mcp module is part of the Spring AI MCP project. It provides Spring Framework integration for the Model Control Protocol (MCP), enabling seamless integration of MCP functionality within Spring applications.
Features
- Spring integration for MCP clients
- Function callback implementation for tool invocations
- Seamless integration with Spring AI's function calling capabilities
Main Components
McpFunctionCallback
The McpFunctionCallback class is the primary component of this module. It implements Spring AI's FunctionCallback interface and provides:
- Integration between Spring AI's function calling system and MCP tools
- Automatic conversion between JSON and Java objects for tool arguments
- Synchronous tool execution support
Usage
To use this module, add the following dependency to your Maven project:
<dependency>
<groupId>org.springframework.experimental</groupId>
<artifactId>spring-ai-mcp</artifactId>
<version>0.3.0-SNAPSHOT</version>
</dependency>
License
This project is licensed under the Apache License 2.0.
Links
Contributing
This is an experimental Spring project. Contributions are welcome! Please refer to the main project's contribution guidelines.