微软playwright-cli 与playwright mcp 对比说明
-
CLI: Modern coding agents increasingly favor CLI–based workflows exposed as SKILLs over MCP because CLI invocations are more token-efficient: they avoid loading large tool schemas and verbose accessibility trees into the model context, allowing agents to act through concise, purpose-built commands. This makes CLI + SKILLs better suited for high-throughput coding agents that must balance browser automation with large codebases, tests, and reasoning within limited context windows.
CLI ：现代编码代理越来越倾向于使用基于 CLI 的工作流（以 SKILL 的形式公开），而不是 MCP，因为 CLI 调用效率更高：它们避免将庞大的工具模式和冗长的可访问性树加载到模型上下文中，从而使代理能够通过简洁的、专门构建的命令执行操作。这使得 CLI + SKILL 更适合高吞吐量的编码代理，这些代理必须在有限的上下文窗口中平衡浏览器自动化、大型代码库、测试和推理。 -
MCP: MCP remains relevant for specialized agentic loops that benefit from persistent state, rich introspection, and iterative reasoning over page structure, such as exploratory automation, self-healing tests, or long-running autonomous workflows where maintaining continuous browser context outweighs token cost concerns. Learn more about Playwright MCP.
MCP ：对于那些受益于持久状态、丰富的内省以及对页面结构进行迭代推理的特殊代理循环，例如探索性自动化、自愈测试或长时间运行的自主工作流（在这些场景中，维护持续的浏览器上下文比令牌成本更为重要），MCP 仍然具有重要意义。了解更多关于 Playwright MCP 的信息。
mcp cli 对比
传统mcp
| mcp | cli | |
|---|---|---|
| 上下文 | 一次性全部加载所有工具 | 基于技能的渐进式加载 |
| 灵活性 | 开发成本高 | 开发成本低 |
| 生态规模 | 1年的生态 | 过去几十年的沉淀 |
| 替代性 | mcp协议，智能体需要支持mcp协议 | agent → mcporter cli → mcp agent不需要支持mcp协议也可以用mcp |
新mcp生态
- agent
- 技能
- cli bash
- mcporter
- mcp
