web-eval-agent
基于LLM的IDE网页应用调试助手. web-eval-agent is a Model Context Protocol (MCP) server maintained by Operative-Sh. It connects to MCP-compatible clients such as Claude Desktop, Cursor, Cline, and other agents that speak the protocol. It exposes 2 tools, including web_app_ux_evaluator and BrowserUse, that an agent can call directly. It is categorized under Development/Debugging, AI/Agent and Tool/IDE.
什么是MCP
本MCP是一个自主调试代理，利用LLM技术直接在代码编辑器（Cursor或Cline）内执行和调试网页应用。它集成Playwright实现浏览器自动化，并提供实时反馈。
如何使用MCP
通过提供的脚本安装，或在IDE中手动配置JSON设置。需要operative.sh的API密钥和全局安装的Playwright。当处理网页应用时，代理将自动激活。
MCP的用途
实现网页应用的自主端到端测试，捕获网络流量，收集控制台错误，并在开发过程中提供即时反馈，无需离开IDE环境。
AIMCP authority
DR and traffic signal for the AIMCP public domain.
Frequently asked questions
What is the web-eval-agent MCP server?
web-eval-agent is a Model Context Protocol server from Operative-Sh. It lets MCP-compatible AI clients call its tools over a standard interface, so agents like Claude, Cursor, and Cline can use it without custom integration.
How do I connect web-eval-agent to my AI client?
Add web-eval-agent to your client's MCP configuration using the stdio or SSE connection shown in the usage examples on this page, then restart the client to load the server.
What tools does web-eval-agent provide?
web-eval-agent provides 2 tools: web_app_ux_evaluator and BrowserUse.
Is web-eval-agent free to use?
web-eval-agent is listed on AIMCP for free. Any API keys or accounts required by the underlying service are set by its provider.
Vernclaw Plugins for OpenClaw
Ready-to-use connectors for SEO data, social reading & content generation. Pay-as-you-go credits with audit logs.