scrapeunblocker-mcp 0.2.1 → 0.2.3

package/dist/index.js

@@ -5,7 +5,7 @@ import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
 import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
 import { z } from "zod";
 import { APIError, ScrapeUnblockerClient } from "scrapeunblocker";
-var VERSION = "0.2.1";
+var VERSION = "0.2.3";
 var DEFAULT_BASE_URL = "https://api.scrapeunblocker.com";
 var API_KEY_HEADER = "x-scrapeunblocker-key";
 function resolveApiKey() {
@@ -45,11 +45,24 @@ ${page}` : `${head}
 
 The target sent no page body.`;
 }
+function noDataExtractedHtml(raw) {
+  if (!raw || raw.data_extracted !== false) return null;
+  return typeof raw.html === "string" ? raw.html : "";
+}
+function noDataExtractedText(url, html) {
+  const head = `No structured data could be extracted from ${url}: the page loaded, but nothing on it matched a structured shape. The call was billed like fetch_html, so the rendered page is returned instead.`;
+  return html.trim() ? `${head}
+
+The rendered HTML follows:
+
+${html}` : head;
+}
 function errorResult(url, err) {
-  const gone = err instanceof APIError ? targetGoneStatus(err.statusCode) : null;
-  if (gone !== null) {
-    const body = err instanceof APIError ? err.body ?? "" : "";
-    return { content: [{ type: "text", text: targetGoneText(url, gone, body) }] };
+  if (err instanceof APIError) {
+    const gone = targetGoneStatus(err.statusCode);
+    if (gone !== null) {
+      return { content: [{ type: "text", text: targetGoneText(url, gone, err.body ?? "") }] };
+    }
   }
   return { content: [{ type: "text", text: errorText(err) }], isError: true };
 }
@@ -277,7 +290,7 @@ server.registerTool(
   "fetch_parsed",
   {
     title: "Fetch AI-parsed page data",
-    description: "Fetch a web page through ScrapeUnblocker and return AI-parsed structured JSON instead of raw HTML (e.g. product details, article content). Best for extracting fields from product, listing or article pages without writing your own HTML parsing.",
+    description: "Fetch a web page through ScrapeUnblocker and return AI-parsed structured JSON instead of raw HTML (e.g. product details, article content). Best for extracting fields from product, listing or article pages without writing your own HTML parsing. If the page holds no structured data, the result says so and returns the rendered HTML instead (billed like fetch_html).",
     inputSchema: {
       url: z.string().url().describe("The absolute URL to fetch and parse."),
       proxy_country: z.string().length(2).optional().describe("Optional ISO country code to route through, e.g. 'US'."),
@@ -292,6 +305,10 @@ server.registerTool(
         proxyCountry: args.proxy_country,
         rulesHint: args.rules_hint
       });
+      const noDataHtml = noDataExtractedHtml(parsed.raw);
+      if (noDataHtml !== null) {
+        return { content: [{ type: "text", text: noDataExtractedText(args.url, noDataHtml) }] };
+      }
       return {
         content: [{ type: "text", text: JSON.stringify(parsed, null, 2) }]
       };

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scrapeunblocker-mcp",
-  "version": "0.2.1",
+  "version": "0.2.3",
   "mcpName": "com.scrapeunblocker/scrapeunblocker-mcp",
   "description": "Model Context Protocol (MCP) server for ScrapeUnblocker - lets Claude fetch any web page's HTML (or AI-parsed JSON) through the ScrapeUnblocker anti-bot API, using your own API key.",
   "keywords": [