fix(seo): canonical self-deindexing on /docs/*, truthful llms.txt, real sitemap dates, RSS feed, breadcrumbs, per-article OG images

- /docs subpages canonicalized to /docs and had no descriptions; each now
  uses pageMetadata with its own path (was: Google could index at most one)
- llms.txt claimed Team EUR 149, RBAC/SLA and BYO-cloud that do not exist;
  regenerated from lib/seo.ts truth + new llms-full.txt with docs content
- sitemap stamped lastModified=now on every request; now real per-route dates
  from new lib/articles.ts registry (single source for guides index/sitemap/RSS)
- new /feed.xml RSS 2.0 route + alternates link in root layout
- articleJsonLd: image (per-guide opengraph-image via lib/og-article.tsx),
  Person author, wordCount; new breadcrumbJsonLd on guides + docs
- GSC verification via NEXT_PUBLIC_GSC_VERIFICATION (documented in .env.example)
- dropped fabricated Enterprise EUR 499 offer from SoftwareApplication JSON-LD
- article-shell: OL/Table/Note primitives for upcoming articles

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SXUwmPVRTD8AKQtio6gCN5

apps/web/app/docs/concepts/page.tsx

@@ -8,12 +8,26 @@ import {
   DocsCode,
   Mono,
 } from '@/components/docs-page';
+import { JsonLd } from '@/components/json-ld';
+import { breadcrumbJsonLd, pageMetadata } from '@/lib/seo';
 
-export const metadata = { title: 'MCP concepts — BuildMyMCPServer docs' };
+export const metadata = pageMetadata({
+  title: 'MCP concepts',
+  description:
+    'What Model Context Protocol is: tools, resources and prompts, the Streamable HTTP transport, and how a client discovers and calls a server.',
+  path: '/docs/concepts',
+});
 
 export default function Concepts() {
   return (
     <>
+      <JsonLd
+        data={breadcrumbJsonLd([
+          { name: 'Home', path: '/' },
+          { name: 'Docs', path: '/docs' },
+          { name: 'MCP concepts', path: '/docs/concepts' },
+        ])}
+      />
       <DocsTitle kicker="Get started">MCP concepts</DocsTitle>
       <DocsLead>
         Model Context Protocol is an open standard from Anthropic for connecting AI assistants to