https://www.e7coding.com/en/tags/tool-use/Recent content in Tool Use on E7CodingHugoenJoyJoyWed, 01 Jul 2026 15:30:00 +0800https://www.e7coding.com/en/posts/model-context-protocol-mcp-introduction/Wed, 01 Jul 2026 15:30:00 +0800Joyhttps://www.e7coding.com/en/posts/model-context-protocol-mcp-introduction/<p>MCP stands for <strong>Model Context Protocol</strong>.</p> <p>Its role is clear: it provides an open protocol for connecting AI applications to external systems. Those systems may be local files, databases, search engines, business APIs, design tools, knowledge bases, or predefined prompts and workflows.</p>https://www.e7coding.com/en/posts/claude-mcp-prompting-tips/Tue, 16 Jun 2026 15:50:00 +0800Joyhttps://www.e7coding.com/en/posts/claude-mcp-prompting-tips/<blockquote> <p>After connecting Claude to <strong>MCP (Model Context Protocol)</strong>, it can read project files, search code, and run commands. But many people find that even after setup, Claude still misses the point. The reason is simple: <strong>MCP gives Claude capability, not context</strong>. Claude must <strong>call tools</strong> before it can see your project. How you ask directly affects whether it calls the right tools and gives useful answers. This article covers six prompting tips and one core principle.</p>https://www.e7coding.com/en/posts/ai-agent-development-guide/Tue, 16 Jun 2026 15:00:00 +0800Joyhttps://www.e7coding.com/en/posts/ai-agent-development-guide/<blockquote> <p><strong>AI agent development</strong> means building a system that can <strong>perceive, reason, plan, call tools, and execute tasks</strong> to achieve a goal. In one sentence: traditional AI, such as a normal chatbot, answers one question at a time; an AI agent is more like a digital worker. Give it a high-level goal, such as &ldquo;analyze this company&rsquo;s financial report and turn it into a 10-slide deck,&rdquo; and it can break the work into steps, gather information, run code, call APIs, and deliver the result.</p>