Firecrawl MCP Server

Instructions

Implementation Reference

• src/index.ts:483-523 (schema)

  Tool schema definition including input schema for firecrawl_extract
  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:960-973 (registration)

  Registration of all tools including firecrawl_extract (EXTRACT_TOOL) in the listTools 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, GENERATE_LLMSTXT_TOOL, ], }));
• src/index.ts:1288-1386 (handler)

  Main handler logic for firecrawl_extract: validates args with isExtractOptions, calls Firecrawl client.extract(), handles response, credits, errors, and formats output
  case 'firecrawl_extract': { if (!isExtractOptions(args)) { throw new Error('Invalid arguments for firecrawl_extract'); } try { const extractStartTime = Date.now(); safeLog( 'info', `Starting extraction for URLs: ${args.urls.join(', ')}` ); // Log if using self-hosted instance if (FIRECRAWL_API_URL) { safeLog('info', '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 safeLog( 'info', `Extraction completed in ${Date.now() - extractStartTime}ms` ); // Add warning to response if present const result = { content: [ { type: 'text', text: trimResponseText(JSON.stringify(response.data, null, 2)), }, ], isError: false, }; if (response.warning) { safeLog('warning', 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') ) { safeLog( 'error', 'Extraction is not supported by this self-hosted instance' ); return { content: [ { type: 'text', text: trimResponseText( 'Extraction is not supported by this self-hosted instance. Please ensure LLM support is configured.' ), }, ], isError: true, }; } return { content: [{ type: 'text', text: trimResponseText(errorMessage) }], isError: true, }; } }
• src/index.ts:738-745 (helper)

  Type guard helper function to validate arguments for firecrawl_extract
  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:661-745 (helper)

  Type interfaces for ExtractArgs and ExtractResponse used by firecrawl_extract handler and validator.
  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; } // Type guards function isScrapeOptions( args: unknown ): args is ScrapeParams & { url: string } { return ( typeof args === 'object' && args !== null && 'url' in args && typeof (args as { url: unknown }).url === 'string' ); } function isMapOptions(args: unknown): args is MapParams & { url: string } { return ( typeof args === 'object' && args !== null && 'url' in args && typeof (args as { url: unknown }).url === 'string' ); } function isCrawlOptions(args: unknown): args is CrawlParams & { url: string } { return ( typeof args === 'object' && args !== null && 'url' in args && typeof (args as { url: unknown }).url === 'string' ); } function isBatchScrapeOptions(args: unknown): args is BatchScrapeOptions { return ( typeof args === 'object' && args !== null && 'urls' in args && Array.isArray((args as { urls: unknown }).urls) && (args as { urls: unknown[] }).urls.every((url) => typeof url === 'string') ); } function isStatusCheckOptions(args: unknown): args is StatusCheckOptions { return ( typeof args === 'object' && args !== null && 'id' in args && typeof (args as { id: unknown }).id === 'string' ); } function isSearchOptions(args: unknown): args is SearchOptions { return ( typeof args === 'object' && args !== null && 'query' in args && typeof (args as { query: unknown }).query === 'string' ); } 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') ); }