소개
This proof-of-concept project demonstrates a dynamic Model Context Protocol (MCP) server built on Cloudflare Workers, Containers, and D1. It enables AI agents, such as Claude, to discover and invoke containerized tools without requiring redeployment of the core service. Tools are registered via a simple HTTP API and stored in D1, with each tool running in an isolated Cloudflare Container, offering secure isolation and serverless scale-to-zero capabilities. The architecture provides a flexible way to extend AI agent functionality with custom or external tools.
주요 기능
- Containerized Execution in isolated Cloudflare Containers
- HTTP API for runtime tool registration
- 0 GitHub stars
- Dynamic Tool Registry via Cloudflare D1
- MCP Protocol for AI agent tool discovery
- Serverless Scale-to-Zero for efficient resource usage
사용 사례
- Extending AI agent capabilities with custom or external tools
- Building a dynamic and scalable tool registry for AI models
- Registering new tools for AI interaction without service redeployment
Sponsored