pagesight 0.14.0 → 0.14.1

package/README.md

@@ -8,34 +8,40 @@ See your site the way search engines and AI see it.
 npm install pagesight
 ```
 
-Your AI assistant can write your code. Now it can see your site. Index status, performance, real-user metrics, search traffic, meta tags, structured data, AI crawler access — one package, one call.
+Your AI assistant can write your code. Now it can see your site. Index status, performance, real-user metrics, search traffic, meta tags, structured data, AI crawler access, link health — one package, one call.
 
 ```
 === Site Audit: https://example.com ===
 
+2 checks failed — results below are partial:
+
+  FAIL  PageSpeed: quota exceeded
+  FAIL  Sitemaps: permission denied
+
+5 findings:
+
 HIGH    Missing canonical URL
-HIGH    7,772 sitemap URLs submitted, 0 indexed
+HIGH    22 sitemap URLs submitted, 0 indexed
+        Auto-inspected 5 URLs:
+        - 2/5 indexed
+        - 3/5 Discovered - currently not indexed: /docs/, /pricing/, /about/
 MEDIUM  Missing og:image — no social preview image
-MEDIUM  Accessibility score: 89/100
 LOW     Missing Twitter Card tags
-LOW     No structured data (JSON-LD) found
+LOW     6/139 AI crawlers blocked
 ```
 
 ## Tools
 
-| Tool | What it does |
-|------|-------------|
-| `audit` | One-call site audit. Runs all checks in parallel. Returns prioritized findings. |
-| `pagespeed` | Lighthouse scores, Core Web Vitals, opportunities, failing audits with fix links. |
-| `metatags` | OG, Twitter Card, canonical, JSON-LD with schema validation, redirect chain, image validation. |
-| `inspect` | Google index status, canonical choice, crawl state, rich results. |
-| `sample_inspect` | Sample URLs from a sitemap and batch-inspect. Diagnoses indexing patterns. |
-| `performance` | Search analytics — clicks, impressions, CTR, position. `compare: true` for period-over-period. |
-| `crux` | Real-user Core Web Vitals (p75, histograms). |
-| `crux_history` | CWV trends over time — up to 40 weekly data points. |
-| `robots` | robots.txt validation (RFC 9309) + AI crawler audit (139+ bots). |
-| `sitemaps` | Search Console properties and sitemaps with submitted/indexed counts. |
-| `setup` | Auth status and OAuth setup. |
+6 tools organized by intent:
+
+| Tool | Intent | What it does |
+|------|--------|-------------|
+| `audit` | How's my site? | One-call site audit. Runs all checks in parallel. Prioritized findings with auto-drill-down on indexing issues. |
+| `page` | What's on this URL? | Meta tags, OG, Twitter Card, JSON-LD validation (19 schema types), internal link health, redirect chains, WCAG contrast checker. Batch mode for multiple URLs. |
+| `speed` | How fast is it? | PageSpeed single/batch/compare with Lighthouse scores and opportunities. CrUX real-user metrics (snapshot + history trends). |
+| `search` | How's Google seeing me? | URL inspection, sample-inspect from sitemaps, sitemap management, search analytics with period-over-period comparison. |
+| `ai` | How's AI seeing me? | AI crawler audit (139+ bots by category), robots.txt validation (RFC 9309), llms.txt detection, path access checks. |
+| `setup` | Auth config | Auth status check and OAuth setup flow. |
 
 ## Setup
 
@@ -58,7 +64,7 @@ Add to your MCP config:
 }
 ```
 
-`robots`, `metatags`, and `pagespeed` work without credentials.
+`page`, `speed`, and `ai` work without credentials. `search` and `audit` (for GSC checks) require OAuth or a service account.
 
 ### Full setup
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pagesight",
-  "version": "0.14.0",
+  "version": "0.14.1",
   "description": "See your site the way search engines and AI see it.",
   "keywords": [
     "seo",

package/src/tools/ai.ts

@@ -12,12 +12,24 @@ interface LlmsTxtResult {
 
 async function checkLlmsTxt(origin: string, path: string): Promise<LlmsTxtResult> {
   try {
+    const controller = new AbortController();
+    const timeout = setTimeout(() => controller.abort(), 10_000);
     const res = await fetch(`${origin}${path}`, {
       headers: { "User-Agent": "Pagesight/1.0" },
       redirect: "follow",
+      signal: controller.signal,
     });
+    clearTimeout(timeout);
     if (!res.ok) return { exists: false, size: null, firstLine: null };
+    // Cap at 1MB to avoid OOM on large responses
+    const contentLength = Number(res.headers.get("content-length") ?? 0);
+    if (contentLength > 1_048_576) {
+      return { exists: true, size: contentLength, firstLine: "(file too large to preview)" };
+    }
     const text = await res.text();
+    if (text.length > 1_048_576) {
+      return { exists: true, size: text.length, firstLine: "(file too large to preview)" };
+    }
     const firstLine =
       text
         .split("\n")
@@ -215,6 +227,7 @@ export function registerAiTool(server: McpServer): void {
     {
       url: z
         .string()
+        .url()
         .describe("Site URL or origin (e.g., 'https://example.com'). Fetches /robots.txt from this origin."),
       check_path: z
         .string()

package/src/tools/page.ts

@@ -615,7 +615,7 @@ async function checkLink(href: string): Promise<LinkResult> {
   try {
     for (let i = 0; i < 10; i++) {
       const res = await fetch(current, {
-        method: "GET",
+        method: "HEAD",
         headers: { "User-Agent": "Mozilla/5.0 (compatible; Googlebot/2.1)", Accept: "text/html" },
         redirect: "manual",
       });

package/src/tools/search.ts

@@ -430,10 +430,16 @@ function formatComparison(
 }
 
 function daysAgo(n: number): string {
-  // GSC dates are in PT (Pacific Time). Use UTC-8 as a stable approximation.
-  const now = new Date(Date.now() - 8 * 60 * 60 * 1000);
-  now.setDate(now.getDate() - n);
-  return now.toISOString().split("T")[0];
+  // GSC dates are in Pacific Time. Use Intl to handle DST correctly.
+  const d = new Date();
+  d.setDate(d.getDate() - n);
+  const parts = new Intl.DateTimeFormat("en-CA", {
+    timeZone: "America/Los_Angeles",
+    year: "numeric",
+    month: "2-digit",
+    day: "2-digit",
+  }).format(d);
+  return parts; // en-CA formats as YYYY-MM-DD
 }
 
 // ── Tool registration ──

package/src/tools/speed.ts

@@ -813,10 +813,10 @@ export function registerSpeedTool(server: McpServer): void {
         const cruxOrigin = origin;
 
         if (!cruxUrl && !cruxOrigin) {
-          return { content: [{ type: "text" as const, text: "Error: provide either url or origin, not both." }] };
+          return { content: [{ type: "text" as const, text: "Error: provide url or origin for CrUX data." }] };
         }
         if (cruxUrl && cruxOrigin) {
-          return { content: [{ type: "text" as const, text: "Error: provide either url or origin, not both." }] };
+          return { content: [{ type: "text" as const, text: "Error: provide url or origin, not both." }] };
         }
 
         try {
@@ -860,10 +860,10 @@ export function registerSpeedTool(server: McpServer): void {
         const histOrigin = origin;
 
         if (!histUrl && !histOrigin) {
-          return { content: [{ type: "text" as const, text: "Error: provide either url or origin, not both." }] };
+          return { content: [{ type: "text" as const, text: "Error: provide url or origin for CrUX history." }] };
         }
         if (histUrl && histOrigin) {
-          return { content: [{ type: "text" as const, text: "Error: provide either url or origin, not both." }] };
+          return { content: [{ type: "text" as const, text: "Error: provide url or origin, not both." }] };
         }
 
         try {