Check AI search visibility: Run check_ai_readiness on any URL to get a 0-100 score, letter grade, and specific fixes for AI-crawler access, JSON-LD structured data, title/meta, Open Graph, sitemap, and llms.txt.
Generate ready-to-paste fixes: Use generate_ai_readiness_fixes to produce starter Organization + FAQPage JSON-LD (pre-filled with the site's real title/description) and an AI-crawler-friendly robots.txt.
Integrate into AI assistants: Expose both tools to any MCP client (Claude Desktop, Cursor, etc.) via stdio or HTTP, enabling simple prompts like "Is my site visible to AI search?" to return scored inline reports.
Checks whether your website is visible to AI search engines, including Claude, Perplexity, and Google AI, by verifying crawler access, structured data, and other factors.
Checks whether your website is visible to AI search engines, including Claude, Perplexity, and Google AI, by verifying crawler access, structured data, and other factors.
Is your website visible to AI search? A tiny, dependency-free CLI that checks whether ChatGPT, Perplexity, Claude, and Google AI can crawl and understand your site, and tells you exactly what to fix.
npx github:epistemedeus/ai-readiness yoursite.comNo install, no signup, no dependencies. Node 18+.
Prefer a browser? Run the same check (no install) at samedaydesk.com/tools/ai-readiness.
The checker tells you what to fix. This kit gives you everything to fix it, ready to paste:
Copy-paste robots.txt (welcomes every AI crawler), Organization + WebSite + FAQPage JSON-LD, title/meta/Open Graph templates, and an XML sitemap
The 7-fix priority checklist in order of impact
The full benchmark behind the dataset below
Delivered instantly after checkout, no signup
→ Get the AI Search Readiness Kit ($9) · Prefer a done-for-you audit of your site? See samedaydesk.com.
We ran this checker against the homepages of 136 well-known companies across 7 industries and published the full results. Open data, free to use with attribution.
Full CSV: data/ai-search-readiness-2026.csv
Interactive, sortable leaderboard: samedaydesk.com: AI-Search Readiness Leaderboard
Average score by industry (lower = harder for AI search to read):
Industry | Avg score | n |
Marketing agencies | 92 | 24 |
SaaS | 88 | 24 |
Dev tools | 86 | 17 |
E-commerce | 85 | 19 |
AI startups | 83 | 25 |
Fintech | 74 | 16 |
Healthtech | 63 | 11 |
Notable findings: Healthtech is the least AI-search-ready industry (avg 63). Klarna scored an F (38); GitHub, Chime, Ramp, Gusto, Ro, Hims and Zocdoc each scored a D. Even some AI companies struggle. Perplexity scored a C and LlamaIndex a D. Most gaps are the same and entirely fixable: JavaScript-only homepages, missing JSON-LD structured data, and no sitemap.
Per-industry write-ups: SaaS · e-commerce · marketing agencies · AI startups · healthtech.
Related MCP server: geo-audit
AI search is becoming how people find things, and AI answers are pulled from a small set of pages that are crawlable and well-structured. If GPTBot is blocked in your robots.txt, or your pages have no structured data, you can be invisible in AI answers no matter how good your site looks to humans. This tool checks the technical fundamentals that decide whether you're even eligible to be cited.
Check | Why it matters |
AI crawler access | Whether |
Structured data (JSON-LD) | AI engines use JSON-LD ( |
Title & meta description | Present and well-sized, so engines have a clean summary to work with. |
Open Graph tags | Richer machine-readable context and clean link previews. |
XML sitemap | Helps engines discover your pages; submit it in Bing Webmaster Tools (ChatGPT Search reads the Bing index). |
llms.txt | Flagged as cheap hygiene only. Honest note: it has no proven effect on AI citations yet, so don't let anyone sell it to you as a ranking boost. |
You get a 0-100 score, a letter grade, and a concrete fix for every failing check.
$ 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)JSON output for scripting: npx github:epistemedeus/ai-readiness yoursite.com --json
Add the checker to any Model Context Protocol client (Claude Desktop, Cursor, Cline, etc.) so you can ask your AI assistant "is my site visible to AI search?" and get a scored report inline. Dependency-free, runs over stdio.
{
"mcpServers": {
"ai-readiness": {
"command": "npx",
"args": ["-y", "github:epistemedeus/ai-readiness", "mcp"]
}
}
}It exposes two tools:
check_ai_readiness(url): returns the score, grade, and a specific fix for each gap.
generate_ai_readiness_fixes(url): generates starter Organization + FAQPage JSON-LD (pre-filled from the site) and an AI-crawler-friendly robots.txt.
This standalone package is the two-tool local MCP server. Use the npx stdio config above (npx -y github:epistemedeus/ai-readiness mcp, or node mcp.js). http.js is a minimal stateless custom JSON-RPC-over-HTTP POST adapter (POST /mcp); it is not MCP Streamable HTTP, not a production remote MCP transport, and ordinary Streamable HTTP clients cannot use it as-is. There is no hosted remote MCP URL for this package.
Fail-fast on AI-search regressions by checking a URL on every deploy:
- uses: epistemedeus/ai-readiness@v1
with:
url: https://yoursite.comThis CLI checks the technical basics. The questions it can't answer from your markup: do ChatGPT, Perplexity, and Google AI actually cite you for the queries your buyers type? How do you compare to named competitors? What's the highest-ROI fix first?
That's the AI-Search Visibility Audit from SameDayDesk: real citation testing across engines, a competitor benchmark, and a prioritized fix list as a PDF and web report, delivered same day. → samedaydesk.com
Like how this one is built: dependency-free, stdio plus a custom JSON-RPC-over-HTTP POST adapter, published to the MCP registry, two focused tools? We build MCP servers for your API or product the same way. (Curious how? Read the guide: How to build a dependency-free MCP server.)
Custom MCP Server: $349, delivered fast. You get a working server (stdio + optional hosted remote), wired to your API, with the registry/manifest setup done. → get one built (or buy directly).
Free, in-depth guides on getting your site read and cited by AI search:
ChatGPT vs Perplexity vs Google AI: which can read your site
AI crawler list 2026: GPTBot, ClaudeBot, PerplexityBot & how to allow them
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
