Anthropic 最新发了篇博客，标题叫《Building agents that reach production systems with MCP》，翻译过来是： 《构建能触达生产系统的 Agent：MCP 实践指南》。 MCP 最新博客 在我去年 11 月的文章《》和上个月的文章《》、《》中，我一直在阐述一个观点： CLI + Skills 才是 Agent 连接外部系统的正道，因为 MC ...

The integration of mCP (Model Context Protocol) servers with Claude Code is reshaping how workflows are designed and executed. By combining server-based protocols, APIs, and custom tools, you can ...

Unsafe defaults in MCP configurations open servers to possible remote code execution, according to security researchers who ...

Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's (MCP) architecture ...

IT之家4 月 16 日消息，网络安全公司 OX Security 昨日（4 月 15 日）发布报告，披露 Anthropic 的 MCP（模型上下文协议）存在设计缺陷，可导致远程代码执行。 该设计缺陷影响范围极广，导致超过 20 万台 AI 服务器面临远程代码执行风险。 IT之家注：MCP 全称为 Model Context Protocol，是 Anthropic 公司于 2024 年 11 ...

Latest VS Code release improves AI agent integration with backing for Model Context Protocol server prompts, resources, sampling, and authorization. Visual Studio Code 1.101, aka the May 2025 version ...

The July 2025 update to Visual Studio Code, taking it to version 1.103, adds support for chat checkpoints, allowing developers to restore their workspace and conversation to earlier states during AI ...

The Claude Code Figma MCP introduces a significant update to design and development workflows, allowing users to push UI designs created in Claude Code directly back to Figma. This two-way integration ...

The MCP flaw reveals a systemic AI security gap, exposing enterprise systems to supply chain attacks and forcing a shift ...

Today’s AI coding agents are impressive. They can generate complex multi-line blocks of code, refactor according to internal style, explain their reasoning in plain English, and more. However, AI ...