AWS 构建 MCP 桥接器，实现云端 AI 代理访问本地工具
原标题：How we built an MCP bridge to give our AgentCore-hosted AI agent access to local MCP tools
AI 摘要
AWS 机器学习博客介绍了一种通过 MCP 桥接器，使云端 AgentCore 托管的 AI 代理能够访问用户本地 MCP 工具的方法。该方案利用 WebSocket 和原生消息传递，在远程 MCP 客户端与本地 MCP 服务器之间建立隧道，解决了云端代理与本地文件（如 Excel）之间的访问问题。文章详细描述了架构、消息流和实现细节，并提供了完整的源代码。
正文节选
How we built an MCP bridge to give our AgentCore-hosted AI agent access to local MCP tools Our agent runs in the cloud, but our users’ spreadsheets live on their laptops. How do you bridge that gap? The Model Context Protocol (MCP) is an open source standard introduced by Anthropic in November 2024 to standardize how AI models connect to external data and tools. MCP follows a client-server architecture where an MCP host, an AI application like Amazon Quick or Claude Code, establishes connections