你的网站对 AI 搜索可见吗？ 一个轻量、零依赖的 CLI 工具，用于检查 ChatGPT、Perplexity、Claude 和 Google AI 能否抓取并理解你的网站，并准确告诉你需要修复什么。
npx github:epistemedeus/ai-readiness yoursite.com无需安装、无需注册、零依赖。Node 18+。
更喜欢用浏览器？在 samedaydesk.com/tools/ai-readiness 运行同样的检查（无需安装）。
检查器告诉你要修什么。这个工具包给你修复所需的一切，可直接粘贴使用：
可直接复制的 robots.txt（欢迎所有 AI 爬虫）、Organization + WebSite + FAQPage JSON-LD、title/meta/Open Graph 模板，以及 XML 站点地图
按影响程度排序的 7 项修复优先级清单
下方数据集背后的完整基准
结账后即时交付，无需注册
→ 获取 AI 搜索就绪工具包（$9） · 更想要一站式网站审计？请查看 samedaydesk.com。
我们使用此检查器对 7 个行业的 136 家知名公司 的首页进行了评分，并发布了完整结果。开放数据，注明出处即可免费使用。
可交互、可排序的排行榜： samedaydesk.com：AI 搜索就绪度排行榜
各行业平均分（分数越低 = AI 搜索越难读取）：
行业 | 平均分 | 数量 |
营销代理机构 | 92 | 24 |
SaaS | 88 | 24 |
开发者工具 | 86 | 17 |
电子商务 | 85 | 19 |
AI 初创公司 | 83 | 25 |
金融科技 | 74 | 16 |
健康科技 | 63 | 11 |
值得注意的发现： 健康科技是 AI 搜索就绪度最低的行业（平均 63 分）。Klarna 得分为 F（38）；GitHub、Chime、Ramp、Gusto、Ro、Hims 和 Zocdoc 均得 D。甚至一些 AI 公司也表现不佳。Perplexity 得 C，LlamaIndex 得 D。大多数差距是相同的，而且完全可以修复：纯 JavaScript 首页、缺少 JSON-LD 结构化数据、没有站点地图。
各行业详细报告：SaaS · 电子商务 · 营销代理机构 · AI 初创公司 · 健康科技。
Related MCP server: geo-audit
AI 搜索正成为人们查找信息的方式，而 AI 回答来自一小部分可抓取且结构良好的页面。如果你的 robots.txt 中屏蔽了 GPTBot，或者你的页面没有结构化数据，那么无论你的网站对人类用户看起来多好，你都可能在 AI 回答中不可见。此工具检查的是决定你是否有资格被引用的技术基础。
检查项 | 为什么重要 |
AI 爬虫访问权限 |
|
结构化数据（JSON-LD） | AI 引擎使用 JSON-LD（ |
标题与 meta 描述 | 存在且大小合适，让引擎有干净的摘要可用。 |
Open Graph 标签 | 更丰富的机器可读上下文和干净的链接预览。 |
XML 站点地图 | 帮助引擎发现你的页面；在 Bing 站长工具中提交（ChatGPT 搜索读取 Bing 索引）。 |
llms.txt | 仅标记为低成本卫生项。诚实说明：目前没有证据表明它对 AI 引用有实际效果，所以别让任何人把它当作排名提升来推销。 |
你会得到 0-100 的分数、字母等级，以及每项失败检查的具体修复方案。
$ npx github:epistemedeus/ai-readiness example.com
AI Readiness https://example.com/
Score 72/100 Grade B
PASS AI crawler access No AI crawler blocked.
FAIL Structured data (JSON-LD) None found.
fix: Add Organization + FAQPage + Article JSON-LD.
PASS Title & meta description title 41 chars, description 132 chars
WARN Open Graph tags 2 og: tags
fix: Add og:title, og:description, og:image, og:url.
PASS XML sitemap found
WARN llms.txt none (minor: no proven citation effect)用于脚本化的 JSON 输出：npx github:epistemedeus/ai-readiness yoursite.com --json
将检查器添加到任何 Model Context Protocol 客户端（Claude Desktop、Cursor、Cline 等），这样你就可以问你的 AI 助手*"我的网站对 AI 搜索可见吗？"*，并直接获得带评分的报告。零依赖，通过 stdio 运行。
{
"mcpServers": {
"ai-readiness": {
"command": "npx",
"args": ["-y", "github:epistemedeus/ai-readiness", "mcp"]
}
}
}它暴露两个工具：
check_ai_readiness(url)：返回分数、等级，以及每个差距的具体修复方案。
generate_ai_readiness_fixes(url)：生成初始的 Organization + FAQPage JSON-LD（根据网站预填）和 AI 爬虫友好的 robots.txt。
这个独立包就是双工具的本地 MCP 服务器。使用上面的 npx stdio 配置（npx -y github:epistemedeus/ai-readiness mcp，或 node mcp.js）。http.js 是一个极简的无状态自定义 JSON-RPC-over-HTTP POST 适配器（POST /mcp）；它不是 MCP Streamable HTTP，不是生产级远程 MCP 传输，普通的 Streamable HTTP 客户端不能直接使用它。此包没有托管的远程 MCP URL。
每次部署时检查一个 URL，快速发现 AI 搜索回归问题：
- uses: epistemedeus/ai-readiness@v1
with:
url: https://yoursite.com这个 CLI 检查的是技术基础。它无法从你的标记中回答的问题：ChatGPT、Perplexity 和 Google AI 是否真的会在你的买家输入查询时引用你？与指名竞争对手相比你表现如何？哪个修复的 ROI 最高、应该先做？
这就是 SameDayDesk 的 AI 搜索可见性审计：跨引擎的真实引用测试、竞争对手基准、以及按优先级排序的修复清单（PDF 和网页报告形式），当日交付。→ samedaydesk.com
就像这个一样：零依赖、stdio 加自定义 JSON-RPC-over-HTTP POST 适配器、发布到 MCP 注册表、两个聚焦的工具？我们以同样的方式为你的 API 或产品构建 MCP 服务器。（好奇怎么做？阅读指南：如何构建零依赖的 MCP 服务器。）
自定义 MCP 服务器：$349，快速交付。 你会得到一个可用的服务器（stdio + 可选托管远程），连接到你的 API，注册表/清单配置已完成。→ 获取定制（或直接购买）。
免费、深入的指南，帮助你的网站被 AI 搜索读取和引用：
MIT © SameDayDesk
Check whether a website is visible to AI search engines (ChatGPT, Perplexity, Claude, Google AI Overviews). Fetches the site + robots.txt and scores AI-crawler access, structured data (JSON-LD), title/meta, Open Graph, sitemap, and llms.txt. Returns a 0-100 score, a letter grade, and a specific fix for each gap.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The website to check, e.g. example.com or https://example.com |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully explains the tool's behavior: fetching the site and robots.txt, scoring multiple factors, and returning a score, grade, and specific fixes. It covers the core actions and outputs without ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, front-loaded with the main action, and contains no filler. Each sentence adds essential information: purpose, process, and output.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the moderate complexity, one required parameter, and no output schema, the description adequately explains the return value (score, grade, fix). It mentions all key components checked, making it complete for an agent to understand what the tool does.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'url' is fully described in the schema (100% coverage). The tool description repeats the same example format, adding no new semantics beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Check whether a website is visible to AI search engines' and details the specific checks (robots.txt, JSON-LD, etc.). It distinguishes from the sibling tool 'generate_ai_readiness_fixes' which focuses on providing fixes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus the sibling or alternatives. While the action is clear, there is no guidance on context or prerequisites (e.g., website must be accessible).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate starter fixes to make a website visible to AI search: Organization + FAQPage JSON-LD (pre-filled from the site's real title/description) and an AI-crawler-friendly robots.txt. Paste the JSON-LD into the homepage and replace robots.txt. This is the free starter version of the same-day Fix Pack.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The website to generate fixes for, e.g. example.com |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool generates starter fixes and that it uses the site's real title/description. However, it does not mention any potential side effects, permissions needed, or limitations beyond being a starter version. For a simple generative tool, this is adequate but not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, consisting of two sentences that immediately convey the tool's purpose and outputs. Every sentence adds value, and the structure is front-loaded with the most important information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with one parameter and no output schema, the description is fairly complete. It explains what outputs are generated and how to apply them. However, it lacks details on prerequisites, error handling, or a precise definition of 'AI search'. Overall, it covers the essential aspects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter (url) with schema description coverage at 100%. The description adds no additional meaning beyond the schema's description. Since schema coverage is high, baseline is 3. No enums or constraints, so no missing nuance.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool generates starter fixes for AI visibility, specifically Organization + FAQPage JSON-LD and an AI-friendly robots.txt. It also distinguishes from the sibling tool 'check_ai_readiness' which checks readiness, while this generates fixes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit instructions on how to use the outputs: paste JSON-LD into homepage <head> and replace robots.txt. Mentions it's a free starter version, implying usage context. Lacks explicit when-not-to-use or alternative scenarios, but the guidance is clear and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
check_ai_readinessgenerate_ai_readiness_fixesEach tool has a distinct purpose: one checks AI readiness, the other generates fixes. No overlap in functionality.
Both tool names follow a consistent verb_noun pattern with snake_case (check_ai_readiness, generate_ai_readiness_fixes).
Two tools is minimal; while the domain is narrow, a server like this might benefit from additional tools like a detailed report or verification tool.
The tools cover checking and generating fixes, but there is no tool to verify fixes after application or to manage multiple websites, leaving some gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Checks llms.txt, AI crawler access in robots.txt, and sitemap - with a 0-100 AI readiness score.
Scan any website's AI readiness: AI search visibility and AI agent usability. Free, no auth.
AEO audit: score any website 0-100 for AI visibility. Checks schema, meta, content, AI crawlers.
Scan any public site for AI-agent visibility; get scored findings, a machine-readable fix pack, and
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/epistemedeus/ai-readiness'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
