mcp-scraper 0.83.3 → 0.83.5

package/CHANGELOG.md

@@ -4,6 +4,19 @@ All notable changes to MCP Scraper are documented here. The format is based on [
 
 ## [Unreleased]
 
+## [0.83.5] - 2026-09-01
+
+### Fixed
+
+- Allowed auto-discovered rules to verify bounded repeated DOM matches, including parallel desktop/mobile navigation and repeated semantic CTAs, instead of falsely treating every selector as unique.
+
+## [0.83.4] - 2026-09-01
+
+### Fixed
+
+- Collapsed repeated route-and-selector setup candidates into one runtime rule, preventing one semantic CTA interaction from emitting duplicate events.
+- Published `data-xray-event` selectors as semantic rules so the Pixel records the element's live CTA placement, component, action, destination, plan, value, currency, and content dimensions.
+
 ## [0.83.3] - 2026-09-01
 
 ### Fixed
@@ -1600,6 +1613,8 @@ All notable changes to MCP Scraper are documented here. The format is based on [
 - Provider-specific connection data is normalized into one agent-facing contract.
 
 [Unreleased]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.83.3...HEAD
+[0.83.5]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.83.4...v0.83.5
+[0.83.4]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.83.3...v0.83.4
 [0.83.3]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.83.2...v0.83.3
 [0.83.2]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.83.1...v0.83.2
 [0.83.1]: https://github.com/VilovietaSEO/mcp-scraper/compare/v0.83.0...v0.83.1

package/README.md

@@ -175,7 +175,7 @@ Build the branded one-click bundle:
 npm run build:mcpb
 ```
 
-The generated bundle is written to `build/mcpb/mcp-scraper-<version>.mcpb` and copied to `public/downloads/` for the hosted download. The current public bundle is `https://mcpscraper.dev/downloads/mcp-scraper.mcpb` (`0.83.3`, SHA-256 `7b13fa6fea7f37a4ae1c546a329323b956cfef823352541d966952c015d817dc`). Install it by opening or dragging it into Claude Desktop. Claude displays the `MCP Scraper` install card, icon, API-key configuration field, and manually curated current-release message from the bundle manifest.
+The generated bundle is written to `build/mcpb/mcp-scraper-<version>.mcpb` and copied to `public/downloads/` for the hosted download. The current public bundle is `https://mcpscraper.dev/downloads/mcp-scraper.mcpb` (`0.83.5`, SHA-256 `ab7a2b9e1fb1d2020e7eeda5ef010279ce6a74effdb7399aff2f748c3ac06022`). Install it by opening or dragging it into Claude Desktop. Claude displays the `MCP Scraper` install card, icon, API-key configuration field, and manually curated current-release message from the bundle manifest.
 
 The MCPB install exposes every tool — web-intelligence plus all `browser_*` tools — through the one `mcp-scraper` server.
 

package/dist/bin/api-server.js

@@ -17,7 +17,7 @@ loadDotEnv();
 async function main() {
   const [{ serve }, { app, personalAssistantProductionStartup }, { startWorker }, { migrate }] = await Promise.all([
     import("@hono/node-server"),
-    import("../server-3WEFWWTX.js"),
+    import("../server-2E4YF6TY.js"),
     import("../worker-FM3ZRDY4.js"),
     import("../db-Z34LPZNR.js")
   ]);

package/dist/bin/mcp-scraper-cli.js

@@ -19,7 +19,7 @@ import {
 import "../chunk-GGZEC22A.js";
 import {
   PACKAGE_VERSION
-} from "../chunk-T5IM6BDD.js";
+} from "../chunk-2B636U7P.js";
 
 // src/cli/human-cli.ts
 import { Command } from "commander";

package/dist/bin/mcp-scraper-core.js

@@ -1,8 +1,8 @@
 #!/usr/bin/env node
 import {
   runMcpScraperStdio
-} from "../chunk-PUSG46S2.js";
-import "../chunk-RHP6AZOJ.js";
+} from "../chunk-VJHMPJR7.js";
+import "../chunk-2BOBOKFQ.js";
 import "../chunk-PGJQDMC2.js";
 import "../chunk-DNM65UCK.js";
 import "../chunk-T3MZISOF.js";
@@ -13,7 +13,7 @@ import "../chunk-OPQIGAFB.js";
 import "../chunk-UXVT7FWW.js";
 import "../chunk-BGD7U3AE.js";
 import "../chunk-GGZEC22A.js";
-import "../chunk-T5IM6BDD.js";
+import "../chunk-2B636U7P.js";
 import "../chunk-YXNDOQXN.js";
 
 // src/mcp/thorbit-restricted-tool-surface.ts

package/dist/bin/mcp-scraper-install.js

@@ -4,7 +4,7 @@ import {
 } from "../chunk-UXVT7FWW.js";
 import {
   PACKAGE_VERSION
-} from "../chunk-T5IM6BDD.js";
+} from "../chunk-2B636U7P.js";
 
 // bin/mcp-scraper-install.ts
 var noColor = process.argv.includes("--no-color") || process.env.NO_COLOR !== void 0 || process.env.FORCE_COLOR === "0" || !process.stdout.isTTY;

package/dist/bin/mcp-stdio-server.js

@@ -1,8 +1,8 @@
 #!/usr/bin/env node
 import {
   runMcpScraperStdio
-} from "../chunk-PUSG46S2.js";
-import "../chunk-RHP6AZOJ.js";
+} from "../chunk-VJHMPJR7.js";
+import "../chunk-2BOBOKFQ.js";
 import "../chunk-PGJQDMC2.js";
 import "../chunk-DNM65UCK.js";
 import "../chunk-T3MZISOF.js";
@@ -13,7 +13,7 @@ import "../chunk-OPQIGAFB.js";
 import "../chunk-UXVT7FWW.js";
 import "../chunk-BGD7U3AE.js";
 import "../chunk-GGZEC22A.js";
-import "../chunk-T5IM6BDD.js";
+import "../chunk-2B636U7P.js";
 import "../chunk-YXNDOQXN.js";
 
 // bin/mcp-stdio-server.ts

package/dist/{chunk-T5IM6BDD.js → chunk-2B636U7P.js}

@@ -1,5 +1,5 @@
 // src/version.ts
-var PACKAGE_VERSION = "0.83.3";
+var PACKAGE_VERSION = "0.83.5";
 
 export {
   PACKAGE_VERSION

package/dist/{chunk-RHP6AZOJ.js → chunk-2BOBOKFQ.js}

@@ -50,7 +50,7 @@ import {
 } from "./chunk-BGD7U3AE.js";
 import {
   PACKAGE_VERSION
-} from "./chunk-T5IM6BDD.js";
+} from "./chunk-2B636U7P.js";
 import {
   PUBLIC_ERROR_CODES,
   buildPublicErrorEnvelope,

package/dist/{chunk-PUSG46S2.js → chunk-VJHMPJR7.js}

@@ -12,13 +12,13 @@ import {
   registerScheduledResultsMcpTools,
   registerSerpIntelligenceCaptureTools,
   resolveDeploymentProfile
-} from "./chunk-RHP6AZOJ.js";
+} from "./chunk-2BOBOKFQ.js";
 import {
   renderInstallTerminal
 } from "./chunk-UXVT7FWW.js";
 import {
   PACKAGE_VERSION
-} from "./chunk-T5IM6BDD.js";
+} from "./chunk-2B636U7P.js";
 
 // src/mcp/stdio-runtime.ts
 import { readFileSync } from "fs";

package/dist/{server-3WEFWWTX.js → server-2E4YF6TY.js}

@@ -373,7 +373,7 @@ import {
   resolveLocalSourcebookSchemaType,
   transcribeMediaUrl,
   transitionAnalyticsExperiment
-} from "./chunk-RHP6AZOJ.js";
+} from "./chunk-2BOBOKFQ.js";
 import {
   auditImageUrls,
   auditImages,
@@ -494,7 +494,7 @@ import {
 } from "./chunk-GGZEC22A.js";
 import {
   PACKAGE_VERSION
-} from "./chunk-T5IM6BDD.js";
+} from "./chunk-2B636U7P.js";
 import {
   CaptchaError,
   MapsSearchIncompletePageError,
@@ -53283,6 +53283,12 @@ async function requireSetupEntitlement(userId) {
     throw new AnalyticsRepositoryError("analytics_entitlement_required", "A current X-Ray entitlement is required for site setup.", 403);
   }
 }
+function analyticsSemanticEventName(selector) {
+  return /^\[data-xray-event=(["'])([a-z][a-z0-9_]{1,79})\1\]$/.exec(selector)?.[2] ?? null;
+}
+function analyticsAutoRuleExpectedMaximum(observedCandidates) {
+  return Math.max(20, Math.min(100, observedCandidates));
+}
 function analyticsSiteSetupService() {
   const db = getAnalyticsPool();
   return new AnalyticsSiteSetupService({
@@ -53295,20 +53301,30 @@ function analyticsSiteSetupService() {
         hex[16] = ["8", "9", "a", "b"][Number.parseInt(hex[16], 16) % 4];
         return `${hex.slice(0, 8).join("")}-${hex.slice(8, 12).join("")}-${hex.slice(12, 16).join("")}-${hex.slice(16, 20).join("")}-${hex.slice(20).join("")}`;
       };
-      const eventRules = record7.candidates.filter((candidate) => candidate.disposition === "recommended" && Boolean(candidate.selector)).slice(0, 250).map((candidate) => ({
-        id: uuidFor(candidate.candidateId),
-        version: 1,
-        name: `xray_${candidate.candidateId}`.slice(0, 120),
-        eventName: candidate.eventName,
-        triggerKind: candidate.action === "submit" ? "form" : "click",
-        selector: candidate.selector,
-        path: candidate.routePath,
-        pathMatch: "exact",
-        hostnames: [hostname],
-        metadata: candidate.context,
-        oncePerSession: false,
-        expectedMatches: { min: 1, max: Math.max(1, Math.min(100, candidate.occurrenceCount || 20)) }
-      }));
+      const groupedCandidates = /* @__PURE__ */ new Map();
+      for (const candidate of record7.candidates.filter((item) => item.disposition === "recommended" && Boolean(item.selector)).slice(0, 250)) {
+        const key3 = `${candidate.routePath}\0${candidate.selector}`;
+        const existing = groupedCandidates.get(key3);
+        if (existing) existing.expectedMatches = Math.min(100, existing.expectedMatches + Math.max(1, candidate.occurrenceCount || 1));
+        else groupedCandidates.set(key3, { candidate, expectedMatches: Math.max(1, Math.min(100, candidate.occurrenceCount || 1)) });
+      }
+      const eventRules = [...groupedCandidates.entries()].map(([groupKey, { candidate, expectedMatches }]) => {
+        const semanticEventName = analyticsSemanticEventName(candidate.selector);
+        return {
+          id: uuidFor(groupKey),
+          version: 1,
+          name: `xray_${candidate.candidateId}`.slice(0, 120),
+          eventName: semanticEventName ?? candidate.eventName,
+          triggerKind: semanticEventName ? "semantic" : candidate.action === "submit" ? "form" : "click",
+          selector: candidate.selector,
+          path: candidate.routePath,
+          pathMatch: "exact",
+          hostnames: [hostname],
+          metadata: candidate.context,
+          oncePerSession: false,
+          expectedMatches: { min: 1, max: analyticsAutoRuleExpectedMaximum(expectedMatches) }
+        };
+      });
       const manifest = await publishAnalyticsRuntimeManifest({
         pool: db,
         ownerUserId: Number(record7.ownerId),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mcp-scraper",
-  "version": "0.83.3",
+  "version": "0.83.5",
   "description": "MCP server for MCP Scraper web intelligence tools",
   "type": "module",
   "main": "./dist/index.cjs",