firecrawl_extract

Instructions

{
  "name": "firecrawl_extract",
  "arguments": {
    "urls": ["https://example.com/page1", "https://example.com/page2"],
    "prompt": "Extract product information including name, price, and description",
    "systemPrompt": "You are a helpful assistant that extracts product information",
    "schema": {
      "type": "object",
      "properties": {
        "name": { "type": "string" },
        "price": { "type": "number" },
        "description": { "type": "string" }
      },
      "required": ["name", "price"]
    },
    "allowExternalLinks": false,
    "enableWebSearch": false,
    "includeSubdomains": false
  }
}

Implementation Reference

• src/index.ts:1195-1287 (handler)

  The handler logic for executing the firecrawl_extract tool. It validates the arguments, calls the Firecrawl client's extract method with retry logic, formats the response, and handles errors including self-hosted limitations.

  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;
  
      // 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:504-580 (schema)

  Tool definition for firecrawl_extract, including name, detailed description, and inputSchema specifying parameters like urls (required), prompt, systemPrompt, schema, etc.

  const EXTRACT_TOOL: Tool = {
    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.
  **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
  - systemPrompt: System prompt to guide the LLM
  - 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",
      "systemPrompt": "You are a helpful assistant that extracts product information",
      "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.
  `,
    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:955-966 (registration)

  Registration of the 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,
      CHECK_CRAWL_STATUS_TOOL,
      SEARCH_TOOL,
      EXTRACT_TOOL,
      DEEP_RESEARCH_TOOL,
      GENERATE_LLMSTXT_TOOL,
    ],
  }));

• src/index.ts:823-831 (helper)

  Type guard helper function to validate that arguments for firecrawl_extract contain a valid array of string URLs.

  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')
    );
  }