scrapeunblocker-mcp 0.2.0 → 0.2.2

package/dist/index.js

@@ -4,8 +4,8 @@
 import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
 import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
 import { z } from "zod";
-import { ScrapeUnblockerClient } from "scrapeunblocker";
-var VERSION = "0.2.0";
+import { APIError, ScrapeUnblockerClient } from "scrapeunblocker";
+var VERSION = "0.2.2";
 var DEFAULT_BASE_URL = "https://api.scrapeunblocker.com";
 var API_KEY_HEADER = "x-scrapeunblocker-key";
 function resolveApiKey() {
@@ -28,6 +28,46 @@ function errorText(err) {
   if (err instanceof Error) return err.message;
   return String(err);
 }
+var TARGET_GONE = /* @__PURE__ */ new Set([404, 410]);
+function targetGoneStatus(status, originStatus) {
+  const origin = Number(originStatus);
+  if (TARGET_GONE.has(origin)) return origin;
+  return TARGET_GONE.has(status) ? status : null;
+}
+function targetGoneText(url, code, page) {
+  const reason = code === 410 ? "Gone" : "Not Found";
+  const head = `The target page does not exist: ${url} answered HTTP ${code} (${reason}). This is the website's own answer, not a block or an API failure. The call was billed, and retrying returns the same result - check the URL instead.`;
+  return page.trim() ? `${head}
+
+The target's own ${code} page follows:
+
+${page}` : `${head}
+
+The target sent no page body.`;
+}
+function isNoDataExtracted(status, body) {
+  if (status !== 422 || !body) return false;
+  try {
+    return JSON.parse(body)?.error === "no_data_extracted";
+  } catch {
+    return false;
+  }
+}
+function noDataExtractedText(url) {
+  return `No structured data could be extracted from ${url}: the page loaded, but nothing on it matched a structured shape. This call was not billed. To get the page itself, call fetch_html for the same URL.`;
+}
+function errorResult(url, err) {
+  if (err instanceof APIError) {
+    const gone = targetGoneStatus(err.statusCode);
+    if (gone !== null) {
+      return { content: [{ type: "text", text: targetGoneText(url, gone, err.body ?? "") }] };
+    }
+    if (isNoDataExtracted(err.statusCode, err.body)) {
+      return { content: [{ type: "text", text: noDataExtractedText(url) }] };
+    }
+  }
+  return { content: [{ type: "text", text: errorText(err) }], isError: true };
+}
 async function getPageSourceRaw(params) {
   const apiKey = resolveApiKey();
   if (!apiKey) throw new Error(MISSING_KEY_MESSAGE);
@@ -46,7 +86,12 @@ async function getPageSourceRaw(params) {
     }
   });
   const text = await response.text();
-  return { status: response.status, ok: response.ok, text };
+  return {
+    status: response.status,
+    ok: response.ok,
+    text,
+    originStatus: response.headers.get("x-origin-status")
+  };
 }
 var server = new McpServer({
   name: "scrapeunblocker",
@@ -159,6 +204,10 @@ server.registerTool(
         time_sleep: args.sleep_seconds,
         steps: JSON.stringify(args.steps)
       });
+      const gone = targetGoneStatus(res.status, res.originStatus);
+      if (gone !== null) {
+        return { content: [{ type: "text", text: targetGoneText(args.url, gone, res.text) }] };
+      }
       if (res.ok) {
         return { content: [{ type: "text", text: res.text }] };
       }
@@ -192,7 +241,7 @@ Fix the selector or step (use list_elements to inspect the page) and retry. The
         isError: true
       };
     } catch (err) {
-      return { content: [{ type: "text", text: errorText(err) }], isError: true };
+      return errorResult(args.url, err);
     }
   }
 );
@@ -213,7 +262,8 @@ server.registerTool(
         list_elements: true,
         proxy_country: args.proxy_country
       });
-      if (!res.ok) {
+      const gone = targetGoneStatus(res.status, res.originStatus);
+      if (!res.ok && gone === null) {
         return {
           content: [
             {
@@ -229,9 +279,12 @@ server.registerTool(
         out = JSON.stringify(JSON.parse(res.text), null, 2);
       } catch {
       }
+      if (gone !== null) {
+        return { content: [{ type: "text", text: targetGoneText(args.url, gone, out) }] };
+      }
       return { content: [{ type: "text", text: out }] };
     } catch (err) {
-      return { content: [{ type: "text", text: errorText(err) }], isError: true };
+      return errorResult(args.url, err);
     }
   }
 );
@@ -239,7 +292,7 @@ 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 (that call is not billed) - use fetch_html for the page itself.",
     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'."),
@@ -258,7 +311,7 @@ server.registerTool(
         content: [{ type: "text", text: JSON.stringify(parsed, null, 2) }]
       };
     } catch (err) {
-      return { content: [{ type: "text", text: errorText(err) }], isError: true };
+      return errorResult(args.url, err);
     }
   }
 );

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scrapeunblocker-mcp",
-  "version": "0.2.0",
+  "version": "0.2.2",
   "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": [