mcp-scraper 0.38.0 → 0.38.2

package/dist/{site-extract-repository-I3VM6WXN.js → site-extract-repository-XSPJTCIL.js}

@@ -26,10 +26,10 @@ import {
   setExtractJobTotal,
   settleExtractJob,
   terminalExtractJobStatus
-} from "./chunk-Q35WZJJK.js";
-import "./chunk-PWPUKR5U.js";
+} from "./chunk-YCI2PNCS.js";
+import "./chunk-AZRPG43B.js";
 import "./chunk-44HZLHDV.js";
-import "./chunk-CSCD2HNS.js";
+import "./chunk-N7KUTTCC.js";
 export {
   abandonExtractSettlement,
   claimFailedExtractJobForRefinalize,
@@ -59,4 +59,4 @@ export {
   settleExtractJob,
   terminalExtractJobStatus
 };
-//# sourceMappingURL=site-extract-repository-I3VM6WXN.js.map
+//# sourceMappingURL=site-extract-repository-XSPJTCIL.js.map

package/dist/{worker-TTFXPPDK.js → worker-XCPU4YSN.js}

@@ -3,20 +3,20 @@ import {
   createHarvestAttemptRecorder,
   harvestProblemResponse,
   serializeHarvestProblem
-} from "./chunk-FSAXLDB3.js";
+} from "./chunk-SFRMFGQ6.js";
 import {
   harvest
-} from "./chunk-LOPKN3YL.js";
+} from "./chunk-NGM237OO.js";
 import {
   browserServiceApiKey,
   runWithCostContext
-} from "./chunk-MA5JBAUZ.js";
+} from "./chunk-EGJKUB4Q.js";
 import "./chunk-K443GQY5.js";
 import "./chunk-CB5C3BPB.js";
 import {
   MC_COSTS,
   serpActualCostMc
-} from "./chunk-PWPUKR5U.js";
+} from "./chunk-AZRPG43B.js";
 import "./chunk-44HZLHDV.js";
 import {
   claimPendingJob,
@@ -25,7 +25,7 @@ import {
   debitMc,
   failJob,
   listHarvestAttempts
-} from "./chunk-CSCD2HNS.js";
+} from "./chunk-N7KUTTCC.js";
 
 // src/api/webhook.ts
 async function deliverWebhook(url, payload, retries = 3) {
@@ -139,4 +139,4 @@ export {
   startWorker,
   tickOnce
 };
-//# sourceMappingURL=worker-TTFXPPDK.js.map
+//# sourceMappingURL=worker-XCPU4YSN.js.map

package/docs/mcp-tool-manifest.generated.json

@@ -1,9 +1,9 @@
 {
-  "generatedAt": "2026-07-28T19:01:51.011Z",
+  "generatedAt": "2026-07-28T22:58:47.729Z",
   "generatedFrom": "dist/bin/mcp-stdio-server.js",
   "serverInfo": {
     "name": "mcp-scraper",
-    "version": "0.38.0"
+    "version": "0.38.2"
   },
   "counts": {
     "unified_stdio": 172
@@ -8222,6 +8222,30 @@
           "url": {
             "type": "string"
           },
+          "stoppedEarly": {
+            "anyOf": [
+              {
+                "type": "object",
+                "properties": {
+                  "code": {
+                    "type": "string"
+                  },
+                  "message": {
+                    "type": "string"
+                  }
+                },
+                "required": [
+                  "code",
+                  "message"
+                ],
+                "additionalProperties": false
+              },
+              {
+                "type": "null"
+              }
+            ],
+            "description": "Present when the crawl stopped before finishing. The returned pages are everything that was captured, and billing covers only those pages - treat the result as partial, not as the whole site."
+          },
           "pageCount": {
             "type": "integer",
             "minimum": 0,
@@ -10211,17 +10235,21 @@
     {
       "name": "google_ads_page_intel",
       "title": "Google Ads Advertiser Intel",
-      "description": "Harvest an advertiser's ad creatives from the Google Ads Transparency Center: format, image URLs, and — for video ads — a YouTube video ID or direct video URL. Accepts advertiserId (from google_ads_search) or a domain.",
+      "description": "Harvest an advertiser's ad creatives from the Google Ads Transparency Center: format, image URLs, and — for video ads — a YouTube video ID or direct video URL. Accepts a domain or advertiserName from google_ads_search (google_ads_search does not return advertiser IDs). A domain may map to several advertiser accounts; this returns the primary one.",
       "inputSchema": {
         "type": "object",
         "properties": {
-          "advertiserId": {
+          "domain": {
             "type": "string",
-            "description": "Google Ads Transparency advertiser ID (starts with AR...). Use one returned by google_ads_search; do not construct one yourself."
+            "description": "A website from google_ads_search.websites (e.g. getviktor.com). Preferred input: people know the website, not the advertiser's registered name. Resolves to whichever advertiser account runs ads for that domain."
           },
-          "domain": {
+          "advertiserName": {
+            "type": "string",
+            "description": "An advertiser name exactly as returned in google_ads_search.advertisers[].name (e.g. \"PPS Plumbing Services\"). Use when the user picked an advertiser rather than a website."
+          },
+          "advertiserId": {
             "type": "string",
-            "description": "A domain (e.g. getviktor.com) whose primary advertiser to inspect when advertiserId is unknown. One of advertiserId or domain is required."
+            "description": "Google Ads Transparency advertiser ID (starts with AR...). Only available if you already have one from a prior page-intel result — google_ads_search does NOT return advertiser IDs. Do not construct one yourself."
           },
           "region": {
             "type": "string",
@@ -10365,7 +10393,7 @@
     {
       "name": "google_ads_search",
       "title": "Google Ads Transparency Search",
-      "description": "Search the Google Ads Transparency Center to find advertisers by domain or brand name. Returns advertisers with advertiser ID and approximate ad count, to pass to google_ads_page_intel.",
+      "description": "Search the Google Ads Transparency Center by brand, person, or website. Returns two lists: advertisers (name, country, approximate ad count) and websites (domains). Neither carries an advertiser ID. Pass a websites[].domain (preferred - users know the website, not the registered advertiser name) or an advertisers[].name to google_ads_page_intel to pull that advertiser's actual ads.",
       "inputSchema": {
         "type": "object",
         "properties": {
@@ -10422,6 +10450,9 @@
                 "name": {
                   "$ref": "#/properties/advertisers/items/properties/advertiserId"
                 },
+                "basedIn": {
+                  "$ref": "#/properties/advertisers/items/properties/advertiserId"
+                },
                 "domain": {
                   "$ref": "#/properties/advertisers/items/properties/advertiserId"
                 },
@@ -10442,19 +10473,45 @@
               "required": [
                 "advertiserId",
                 "name",
+                "basedIn",
                 "domain",
                 "approxAdCount",
                 "detailUrl"
               ],
               "additionalProperties": false
             }
+          },
+          "websiteCount": {
+            "type": "integer",
+            "minimum": 0
+          },
+          "websites": {
+            "type": "array",
+            "items": {
+              "type": "object",
+              "properties": {
+                "domain": {
+                  "type": "string"
+                },
+                "detailUrl": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "domain",
+                "detailUrl"
+              ],
+              "additionalProperties": false
+            }
           }
         },
         "required": [
           "query",
           "region",
           "advertiserCount",
-          "advertisers"
+          "advertisers",
+          "websiteCount",
+          "websites"
         ],
         "additionalProperties": false,
         "$schema": "http://json-schema.org/draft-07/schema#"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mcp-scraper",
-  "version": "0.38.0",
+  "version": "0.38.2",
   "description": "MCP server for MCP Scraper web intelligence tools",
   "type": "module",
   "main": "./dist/index.cjs",
@@ -62,7 +62,9 @@
     "email:avatar": "node --import tsx scripts/email/generate-sender-avatar.ts",
     "email:inbound:setup": "node --import tsx scripts/email/setup-resend-inbound.ts",
     "email:audience": "node scripts/run-ts-sandbox-safe.mjs scripts/email/sync-resend-audience.ts",
-    "email:drafts": "node scripts/run-ts-sandbox-safe.mjs scripts/email/create-resend-drafts.ts"
+    "email:drafts": "node scripts/run-ts-sandbox-safe.mjs scripts/email/create-resend-drafts.ts",
+    "billing:preview-credit-lot-repair": "node --import tsx scripts/billing/preview-credit-lot-repair.ts",
+    "billing:apply-credit-lot-repair": "node --import tsx scripts/billing/apply-credit-lot-repair.ts"
   },
   "dependencies": {
     "@anthropic-ai/sdk": "^0.96.0",