scrapeunblocker-mcp 0.2.0 → 0.2.1

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 = "0.2.1";
 var DEFAULT_BASE_URL = "https://api.scrapeunblocker.com";
 var API_KEY_HEADER = "x-scrapeunblocker-key";
 function resolveApiKey() {
@@ -28,6 +28,31 @@ 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 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) }] };
+  }
+  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 +71,12 @@ 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 +189,10 @@ 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 +226,7 @@ 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 +247,8 @@ 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 +264,12 @@ 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);
     }
   }
 );
@@ -258,7 +296,7 @@ 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": "0.2.1",
   "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": [