Development Tools MCP Server

Instructions

Implementation Reference

• src/scrapers/static-scraper.ts:118-121 (handler)

  The extractText method in StaticScraper class, which executes the core logic for the 'extract_text' tool by scraping the HTML and returning the plain text content.

  async extractText(config: ScrapingConfig): Promise<string> {
    const data = await this.scrapeHTML(config);
    return data.text || '';
  }

• src/tools/web-scraping.ts:293-300 (handler)

  Dispatch handler in handleWebScrapingTool function that handles the 'extract_text' tool invocation, choosing between static and dynamic scrapers based on config.

  case 'extract_text': {
    if (config.useBrowser) {
      const data = await dynamicScraper.scrapeDynamicContent(config);
      return data.text;
    } else {
      return await staticScraper.extractText(config);
    }
  }

• src/tools/web-scraping.ts:36-54 (schema)

  Tool registration entry defining the name, description, and input schema for the 'extract_text' tool.

  {
    name: 'extract_text',
    description: 'Extract text content from a web page',
    inputSchema: {
      type: 'object',
      properties: {
        url: {
          type: 'string',
          description: 'URL to scrape',
        },
        useBrowser: {
          type: 'boolean',
          description: 'Use browser for dynamic content',
          default: false,
        },
      },
      required: ['url'],
    },
  },

• src/tools/web-scraping.ts:36-54 (registration)

  Registration of the 'extract_text' tool within the webScrapingTools export array for MCP integration.

  {
    name: 'extract_text',
    description: 'Extract text content from a web page',
    inputSchema: {
      type: 'object',
      properties: {
        url: {
          type: 'string',
          description: 'URL to scrape',
        },
        useBrowser: {
          type: 'boolean',
          description: 'Use browser for dynamic content',
          default: false,
        },
      },
      required: ['url'],
    },
  },