setup-mcp-server — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited setup-mcp-server (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Set up an MCP (Model Context Protocol) server for your website using Inlay. This lets AI agents like Claude, ChatGPT, and others interact with your site programmatically — searching pages, retrieving content, and using your site's functionality.
MCP (Model Context Protocol) is a standard that lets AI agents connect to external tools and data sources. An MCP server for your website gives AI agents tools like:
get_site_info — Get site metadata and descriptionsearch_pages — Search your site's contentget_page_content — Retrieve specific page contentlist_pages — Browse available pagesAdd the Inlay embed script to your site. This enables Inlay to index your content and serve it via MCP.
Next.js (App Router):
// app/layout.tsx
import Script from 'next/script'
export default function RootLayout({ children }) {
return (
<html>
<body>
{children}
<Script
src="https://cdn.inlay.dev/embed.js"
data-site-id="YOUR_SITE_ID"
strategy="afterInteractive"
/>
</body>
</html>
)
}Next.js (Pages Router):
// pages/_app.tsx
import Script from 'next/script'
export default function App({ Component, pageProps }) {
return (
<>
<Component {...pageProps} />
<Script
src="https://cdn.inlay.dev/embed.js"
data-site-id="YOUR_SITE_ID"
strategy="afterInteractive"
/>
</>
)
}Astro:
<!-- src/layouts/Base.astro -->
<script src="https://cdn.inlay.dev/embed.js" data-site-id="YOUR_SITE_ID"></script>Plain HTML:
<script src="https://cdn.inlay.dev/embed.js" data-site-id="YOUR_SITE_ID"></script>Replace YOUR_SITE_ID with the Site ID from your Inlay dashboard.
Once the embed script is installed and Inlay has indexed your site, your MCP endpoint is available at:
https://mcp.inlay.dev/YOUR_SITE_SLUGTest it:
# Check MCP endpoint is responding
curl -s https://mcp.inlay.dev/YOUR_SITE_SLUG
# List available tools
curl -s -X POST https://mcp.inlay.dev/YOUR_SITE_SLUG \
-H 'Content-Type: application/json' \
-d '{"method":"tools/list"}'Test each tool to make sure it works:
# Get site info
curl -s -X POST https://mcp.inlay.dev/YOUR_SITE_SLUG \
-H 'Content-Type: application/json' \
-d '{"method":"tools/call","params":{"name":"get_site_info","arguments":{}}}'
# Search pages
curl -s -X POST https://mcp.inlay.dev/YOUR_SITE_SLUG \
-H 'Content-Type: application/json' \
-d '{"method":"tools/call","params":{"name":"search_pages","arguments":{"query":"getting started"}}}'
# Get specific page content
curl -s -X POST https://mcp.inlay.dev/YOUR_SITE_SLUG \
-H 'Content-Type: application/json' \
-d '{"method":"tools/call","params":{"name":"get_page_content","arguments":{"path":"/"}}}'Make your MCP server discoverable:
## MCP
- Endpoint: https://mcp.inlay.dev/YOUR_SITE_SLUG
- Tools: get_site_info, search_pages, get_page_content, list_pages<meta name="mcp-server" content="https://mcp.inlay.dev/YOUR_SITE_SLUG">Run an AI readiness audit to confirm MCP is detected:
curl -s -X POST https://www.inlay.dev/api/audit \
-H 'Content-Type: application/json' \
-d '{"url":"https://YOUR_SITE"}'The MCP Server category score should now be high.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.