firecrawl_extract
Extract structured data from web pages using LLM prompts and JSON schemas. Supports cloud AI or self-hosted models for web content analysis.
Instructions
Extract structured information from web pages using LLM. Supports both cloud AI and self-hosted LLM extraction.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | List of URLs to extract information from | |
| prompt | No | Prompt for the LLM extraction | |
| systemPrompt | No | System prompt for LLM extraction | |
| schema | No | JSON schema for structured data extraction | |
| allowExternalLinks | No | Allow extraction from external links | |
| enableWebSearch | No | Enable web search for additional context | |
| includeSubdomains | No | Include subdomains in extraction |
Implementation Reference
- src/index.ts:1171-1272 (handler)Main execution handler for firecrawl_extract tool. Validates arguments, calls Firecrawl client.extract with parameters and retry logic, processes response including credits and warnings, handles errors with special case for self-hosted instances.case 'firecrawl_extract': { if (!isExtractOptions(args)) { throw new Error('Invalid arguments for firecrawl_extract'); } try { const extractStartTime = Date.now(); server.sendLoggingMessage({ level: 'info', data: `Starting extraction for URLs: ${args.urls.join(', ')}`, }); // Log if using self-hosted instance if (FIRECRAWL_API_URL) { server.sendLoggingMessage({ level: 'info', data: 'Using self-hosted instance for extraction', }); } const extractResponse = await withRetry( async () => client.extract(args.urls, { prompt: args.prompt, systemPrompt: args.systemPrompt, schema: args.schema, allowExternalLinks: args.allowExternalLinks, enableWebSearch: args.enableWebSearch, includeSubdomains: args.includeSubdomains, origin: 'mcp-server', } as ExtractParams), 'extract operation' ); // Type guard for successful response if (!('success' in extractResponse) || !extractResponse.success) { throw new Error(extractResponse.error || 'Extraction failed'); } const response = extractResponse as ExtractResponse; // Monitor credits for cloud API if (!FIRECRAWL_API_URL && hasCredits(response)) { await updateCreditUsage(response.creditsUsed || 0); } // Log performance metrics server.sendLoggingMessage({ level: 'info', data: `Extraction completed in ${Date.now() - extractStartTime}ms`, }); // Add warning to response if present const result = { content: [ { type: 'text', text: JSON.stringify(response.data, null, 2), }, ], isError: false, }; if (response.warning) { server.sendLoggingMessage({ level: 'warning', data: response.warning, }); } return result; } catch (error) { const errorMessage = error instanceof Error ? error.message : String(error); // Special handling for self-hosted instance errors if ( FIRECRAWL_API_URL && errorMessage.toLowerCase().includes('not supported') ) { server.sendLoggingMessage({ level: 'error', data: 'Extraction is not supported by this self-hosted instance', }); return { content: [ { type: 'text', text: 'Extraction is not supported by this self-hosted instance. Please ensure LLM support is configured.', }, ], isError: true, }; } return { content: [{ type: 'text', text: errorMessage }], isError: true, }; } }
- src/index.ts:482-522 (schema)Tool schema definition for firecrawl_extract, including input validation schema with properties for urls, prompts, schema, and extraction options.const EXTRACT_TOOL: Tool = { name: 'firecrawl_extract', description: 'Extract structured information from web pages using LLM. ' + 'Supports both cloud AI and self-hosted LLM extraction.', inputSchema: { type: 'object', properties: { urls: { type: 'array', items: { type: 'string' }, description: 'List of URLs to extract information from', }, prompt: { type: 'string', description: 'Prompt for the LLM extraction', }, systemPrompt: { type: 'string', description: 'System prompt for LLM extraction', }, schema: { type: 'object', description: 'JSON schema for structured data extraction', }, allowExternalLinks: { type: 'boolean', description: 'Allow extraction from external links', }, enableWebSearch: { type: 'boolean', description: 'Enable web search for additional context', }, includeSubdomains: { type: 'boolean', description: 'Include subdomains in extraction', }, }, required: ['urls'], }, };
- src/index.ts:862-874 (registration)Registration of firecrawl_extract tool (as EXTRACT_TOOL) in the list of available tools returned by ListToolsRequestSchema handler.server.setRequestHandler(ListToolsRequestSchema, async () => ({ tools: [ SCRAPE_TOOL, MAP_TOOL, CRAWL_TOOL, BATCH_SCRAPE_TOOL, CHECK_BATCH_STATUS_TOOL, CHECK_CRAWL_STATUS_TOOL, SEARCH_TOOL, EXTRACT_TOOL, DEEP_RESEARCH_TOOL, ], }));
- src/index.ts:667-674 (helper)Type guard helper function to validate input arguments for firecrawl_extract tool, ensuring urls is a non-empty array of strings.function isExtractOptions(args: unknown): args is ExtractArgs { if (typeof args !== 'object' || args === null) return false; const { urls } = args as { urls?: unknown }; return ( Array.isArray(urls) && urls.every((url): url is string => typeof url === 'string') ); }
- src/index.ts:579-608 (helper)TypeScript interfaces defining parameters, arguments, and response for the firecrawl_extract tool operations.// Add after other interfaces interface ExtractParams<T = any> { prompt?: string; systemPrompt?: string; schema?: T | object; allowExternalLinks?: boolean; enableWebSearch?: boolean; includeSubdomains?: boolean; origin?: string; } interface ExtractArgs { urls: string[]; prompt?: string; systemPrompt?: string; schema?: object; allowExternalLinks?: boolean; enableWebSearch?: boolean; includeSubdomains?: boolean; origin?: string; } interface ExtractResponse<T = any> { success: boolean; data: T; error?: string; warning?: string; creditsUsed?: number; }