Firecrawl MCP Server

Instructions

Implementation Reference

• src/index.ts:550-618 (registration)

  Registration of the 'firecrawl_extract' tool using server.addTool, including description, schema, and handler.
  server.addTool({ name: 'firecrawl_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": "firecrawl_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: unknown, { session, log }: { session?: SessionData; log: Logger } ): Promise<string> => { const client = getClient(session); const a = args as Record<string, unknown>; log.info('Extracting from URLs', { count: Array.isArray(a.urls) ? a.urls.length : 0, }); const extractBody = removeEmptyTopLevel({ urls: a.urls as string[], prompt: a.prompt as string | undefined, schema: (a.schema as Record<string, unknown>) || undefined, allowExternalLinks: a.allowExternalLinks as boolean | undefined, enableWebSearch: a.enableWebSearch as boolean | undefined, includeSubdomains: a.includeSubdomains as boolean | undefined, origin: ORIGIN, }); const res = await client.extract(extractBody as any); return asText(res); }, });
• src/index.ts:597-617 (handler)

  Handler function that gets the Firecrawl client, prepares the extract body by removing empty fields, calls client.extract(), and returns JSON stringified result.
  execute: async ( args: unknown, { session, log }: { session?: SessionData; log: Logger } ): Promise<string> => { const client = getClient(session); const a = args as Record<string, unknown>; log.info('Extracting from URLs', { count: Array.isArray(a.urls) ? a.urls.length : 0, }); const extractBody = removeEmptyTopLevel({ urls: a.urls as string[], prompt: a.prompt as string | undefined, schema: (a.schema as Record<string, unknown>) || undefined, allowExternalLinks: a.allowExternalLinks as boolean | undefined, enableWebSearch: a.enableWebSearch as boolean | undefined, includeSubdomains: a.includeSubdomains as boolean | undefined, origin: ORIGIN, }); const res = await client.extract(extractBody as any); return asText(res); },
• src/index.ts:589-596 (schema)

  Zod schema defining the input parameters: urls (required array), optional prompt, schema, allowExternalLinks, enableWebSearch, includeSubdomains.
  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(), }),
• src/index.ts:164-166 (helper)

  Helper function to stringify data to formatted JSON, used in handler to return results.
  function asText(data: unknown): string { return JSON.stringify(data, null, 2); }
• src/index.ts:142-162 (helper)

  Helper function to create and return FirecrawlApp client instance based on session and env vars.
  function getClient(session?: SessionData): FirecrawlApp { // For cloud service, API key is required if (process.env.CLOUD_SERVICE === 'true') { if (!session || !session.firecrawlApiKey) { throw new Error('Unauthorized'); } return createClient(session.firecrawlApiKey); } // For self-hosted instances, API key is optional if FIRECRAWL_API_URL is provided if ( !process.env.FIRECRAWL_API_URL && (!session || !session.firecrawlApiKey) ) { throw new Error( 'Unauthorized: API key is required when not using a self-hosted instance' ); } return createClient(session?.firecrawlApiKey); }