End-to-End Tooling System with Vertex AI Gemini

Acerca de

This repository provides a comprehensive implementation of the Model Context Protocol (MCP), showcasing how to construct a production-aligned MCP server and client. The system facilitates machine-to-machine communication via JSON-RPC 2.0 over STDIO and leverages Vertex AI Gemini for intelligent tool discovery, execution, and multi-step tool chaining. It integrates securely with Google Cloud using IAM-based authentication, emphasizing protocol correctness, async-safe system design, and real-world LLM tool orchestration patterns to serve as a robust foundation for MCP-based agent systems.

Características Principales

• MCP server built using FastMCP
• STDIO-based JSON-RPC communication
• Multi-round tool chaining using a proper loop
• Vertex AI Gemini integration (IAM-based auth)
• Async-safe lifecycle management with AsyncExitStack
• 0 GitHub stars

Casos de Uso

• Developing LLM-orchestrated applications with multi-step tool chaining
• Integrating Vertex AI Gemini securely for intelligent tool management
• Building production-quality MCP-based agent systems