Store Scraper MCP

Instructions

Implementation Reference

• src/server.js:867-895 (handler)

  Main handler function for 'gp_categories' tool. Fetches the Google Play apps page using buildCategoriesUrl, parses categories with parseCategories, and returns JSON with categories list and count.

  async function handleGPCategories(args) {
    try {
      const url = buildCategoriesUrl();
      const html = await fetchText(url);
      const categories = parseCategories(html);
  
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({
              categories,
              count: categories.length,
            }, null, 2),
          },
        ],
      };
    } catch (error) {
      return {
        content: [
          {
            type: 'text',
            text: JSON.stringify({ error: error.message }, null, 2),
          },
        ],
        isError: true,
      };
    }
  }

• src/server.js:1405-1411 (schema)

  Tool schema definition in the list of tools, specifying name, description, and empty input schema (no parameters required).

    name: 'gp_categories',
    description: '[Google Play] Get list of available categories',
    inputSchema: {
      type: 'object',
      properties: {},
    },
  },

• src/server.js:1482-1483 (registration)

  Dispatch registration in the CallToolRequestSchema switch statement that maps 'gp_categories' tool calls to the handleGPCategories handler.

  case 'gp_categories':
    return await handleGPCategories(args);

• src/parsers/googlePlay/categories.js:10-101 (helper)

  Helper function that parses HTML from Google Play to extract category IDs using regex on links and scripts, with fallback to a hardcoded list of common categories.

  export function parseCategories(html) {
    if (!html || typeof html !== 'string') {
      return [];
    }
  
    const categories = [];
  
    try {
      // Google Play categories are in navigation/dropdown menus
      // Look for category links
      const categoryLinkMatches = html.matchAll(/<a[^>]*href=["'][^"']*\/store\/apps\/category\/([^/"']+)["'][^>]*>/gi);
      
      for (const match of categoryLinkMatches) {
        const category = match[1];
        if (category && !categories.includes(category)) {
          categories.push(category);
        }
      }
  
      // Also try extracting from script tags with category data
      const scriptMatches = html.matchAll(/<script[^>]*>([\s\S]*?)<\/script>/gi);
      
      for (const match of scriptMatches) {
        const scriptContent = match[1];
        
        if (scriptContent.includes('category') || scriptContent.includes('CATEGORY')) {
          try {
            // Try to find category arrays
            const categoryArrayMatch = scriptContent.match(/categories["']?\s*:\s*\[([\s\S]*?)\]/i);
            if (categoryArrayMatch) {
              const categoryData = categoryArrayMatch[1];
              const categoryMatches = categoryData.matchAll(/"([^"]+)"/g);
              
              for (const catMatch of categoryMatches) {
                const category = catMatch[1];
                if (category && !categories.includes(category)) {
                  categories.push(category);
                }
              }
            }
          } catch (e) {
            // Continue
          }
        }
      }
  
      // If no categories found, return common ones
      if (categories.length === 0) {
        return [
          'APPLICATION',
          'GAME',
          'ART_AND_DESIGN',
          'AUTO_AND_VEHICLES',
          'BEAUTY',
          'BOOKS_AND_REFERENCE',
          'BUSINESS',
          'COMICS',
          'COMMUNICATION',
          'DATING',
          'EDUCATION',
          'ENTERTAINMENT',
          'EVENTS',
          'FINANCE',
          'FOOD_AND_DRINK',
          'HEALTH_AND_FITNESS',
          'HOUSE_AND_HOME',
          'LIBRARIES_AND_DEMO',
          'LIFESTYLE',
          'MAPS_AND_NAVIGATION',
          'MEDICAL',
          'MUSIC_AND_AUDIO',
          'NEWS_AND_MAGAZINES',
          'PARENTING',
          'PERSONALIZATION',
          'PHOTOGRAPHY',
          'PRODUCTIVITY',
          'SHOPPING',
          'SOCIAL',
          'SPORTS',
          'TOOLS',
          'TRAVEL_AND_LOCAL',
          'VIDEO_PLAYERS',
          'WEATHER',
        ];
      }
  
      return categories.sort();
    } catch (error) {
      console.error('Error parsing Google Play categories:', error);
      return [];
    }
  }

• src/endpoints/googlePlay.js:180-182 (helper)

  Helper function that builds the URL for the Google Play apps store page to scrape categories from.

  export function buildCategoriesUrl() {
    return `${GOOGLE_PLAY_BASE}/store/apps`;
  }