scorchcrawl-mcp 2.2.0 → 2.3.0

package/dist/index.js

@@ -622,75 +622,6 @@ Check the status of a crawl job.
         }, { tool: 'scorch_check_crawl_status' });
     },
 });
-server.addTool({
-    name: 'scorch_extract',
-    description: `
-Extract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.
-
-**Best for:** Extracting specific structured data like prices, names, details from web pages.
-**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.
-**Arguments:**
-- urls: Array of URLs to extract information from
-- prompt: Custom prompt for the LLM extraction
-- schema: JSON schema for structured data extraction
-- allowExternalLinks: Allow extraction from external links
-- enableWebSearch: Enable web search for additional context
-- includeSubdomains: Include subdomains in extraction
-**Prompt Example:** "Extract the product name, price, and description from these product pages."
-**Usage Example:**
-\`\`\`json
-{
-  "name": "scorch_extract",
-  "arguments": {
-    "urls": ["https://example.com/page1", "https://example.com/page2"],
-    "prompt": "Extract product information including name, price, and description",
-    "schema": {
-      "type": "object",
-      "properties": {
-        "name": { "type": "string" },
-        "price": { "type": "number" },
-        "description": { "type": "string" }
-      },
-      "required": ["name", "price"]
-    },
-    "allowExternalLinks": false,
-    "enableWebSearch": false,
-    "includeSubdomains": false
-  }
-}
-\`\`\`
-**Returns:** Extracted structured data as defined by your schema.
-`,
-    parameters: z.object({
-        urls: z.array(z.string()),
-        prompt: z.string().optional(),
-        schema: z.record(z.string(), z.any()).optional(),
-        allowExternalLinks: z.boolean().optional(),
-        enableWebSearch: z.boolean().optional(),
-        includeSubdomains: z.boolean().optional(),
-    }),
-    execute: async (args, { session, log }) => {
-        const a = args;
-        return safeExecute(async () => {
-            const client = getClient(session);
-            log.info('Extracting from URLs', {
-                count: Array.isArray(a.urls) ? a.urls.length : 0,
-            });
-            const extractBody = removeEmptyTopLevel({
-                urls: a.urls,
-                prompt: a.prompt,
-                schema: a.schema || undefined,
-                allowExternalLinks: a.allowExternalLinks,
-                enableWebSearch: a.enableWebSearch,
-                includeSubdomains: a.includeSubdomains,
-                origin: ORIGIN,
-            });
-            const res = await client.extract(extractBody);
-            // Extract returns structured data — skip summarization
-            return await processResponse(res, { skipSummarization: true });
-        }, { tool: 'scorch_extract' });
-    },
-});
 const PORT = Number(process.env.PORT || 3000);
 const HOST = process.env.CLOUD_SERVICE === 'true'
     ? '0.0.0.0'

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scorchcrawl-mcp",
-  "version": "2.2.0",
+  "version": "2.3.0",
   "description": "Open-source MCP server for web scraping with stealth bot-detection bypass.",
   "type": "module",
   "bin": {