io.github.GlassCaseOfEmotion由 GitHub 账号 GlassCaseOfEmotion 发布v1.0.0更新于 Oct 25, 2026
Scan any website's AI readiness: AI search visibility and AI agent usability. Free, no auth.
AgentGauge 扫描网站的 AI 就绪度，评估 AI 搜索能否找到并引用该网站，以及 AI 智能体能否使用它。
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/io.github.GlassCaseOfEmotion%2Fagentgauge/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": {
"agentgauge": {
"type": "http",
"url": "https://mcp.agentgauge.ai/mcp"
}
}
}Scan any website's AI readiness from inside your AI coding tool — then let it fix the findings in your codebase and re-scan to verify.
AgentGauge grades whether AI search can find you (citability, llms.txt, schema, AI-crawler access) and whether AI agents can use you (tools, identity, commerce signals), against the AgentReady standard with stable AR-IDs and MUST/SHOULD/MAY conformance. Free scan, instant letter grade.
Cursor / Claude Desktop JSON config:
No auth. One tool: scan_website({ url }).
Copy SKILL.md into your Claude Code skills directory as agentgauge/SKILL.md:
or just ask: "check my site's AI readiness and fix what's failing". The skill scans, prioritizes the findings (spec MUSTs first), implements fixes in your repo, and re-scans after deploy to verify the grade actually moved.
31 checks across 6 categories: Discoverability, Content for Agents, AI Visibility (GEO), Capabilities (MCP/A2A/OpenAPI), Identity & Access, and Commerce.
Built by AgentGauge · Weekly monitoring: Watch by AgentGauge · Contact: [email protected]
来源：README.md，提交 51dc765
Scan a website for AI readiness
Run an AgentGauge agent-readiness scan of a website. Grades whether AI search can find/cite it and whether AI agents can use/transact with it, against the AgentReady standard. Returns the grade, both gauges, every check with its status, and a link to the full report.
url必填已满足适用检查项的 100%
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。
claude mcp add --transport http agentgauge https://mcp.agentgauge.ai/mcp{ "mcpServers": { "agentgauge": { "url": "https://mcp.agentgauge.ai/mcp" } }}mkdir -p ~/.claude/skills/agentgaugecurl -fsSL https://raw.githubusercontent.com/GlassCaseOfEmotion/agentgauge-skill/main/SKILL.md \ -o ~/.claude/skills/agentgauge/SKILL.md/agentgauge scan mysite.com