it.sneeze.agentready由 agentready.sneeze.it 发布官方发布者v1.0.0更新于 Oct 24, 2026
Score any website out of 100 for how well AI agents can find, understand and use it.
Agent Ready 为公开网站按 AI 智能体能否找到、理解和使用它打分（满分 100），并解释各项发现。
Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/it.sneeze.agentready%2Fagent-ready/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"agent-ready": {
"type": "http",
"url": "https://agentready.sneeze.it/mcp"
}
}
}Scan a website for agent readiness
Score any public website out of 100 for how well AI agents can use it: reach it, understand it, act on it (book, quote, buy), complete the task, act for a signed-in customer, trust its facts, and find the right location. Returns the score, a score per area, the most important finding in each area, and a link to the full report with every finding and the ordered fix plan. Takes 5 to 20 seconds.
url必填freshGet an existing Agent Ready report
Fetch a report that was already run, by its report link or id, without scanning again.
report必填Explain one Agent Ready check
Explain what one check measures, what it is worth and where to read how to fix it. Pass the check name as it appears in a report, for example "WebMCP tools an agent can call".
check必填How the Agent Ready score works
The scored areas, their weights and every check, so a score can be explained.
无需输入参数。
已满足适用检查项的 83%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
请声明包含 README 的 GitHub 仓库，或在 OAuth 受保护资源元数据中提供 resource_documentation。
托管服务按其提供方的条款使用，因此这里不要求许可证。此检查项不计入百分比。