Bright Data Web MCP

Instructions

Implementation Reference

• server.js:687-743 (handler)

  The execute handler for the web_data_amazon_product_search tool. Triggers the BrightData Datasets API v3 to run the dataset 'gd_lwdb4vjm1ehb499uxs', polls the snapshot status until complete or timeout, and returns the JSON string of collected data.
  execute: tool_fn(`web_data_${id}`, async(data, ctx)=>{ let trigger_response = await axios({ url: 'https://api.brightdata.com/datasets/v3/trigger', params: {dataset_id, include_errors: true}, method: 'POST', data: [data], headers: api_headers(), }); if (!trigger_response.data?.snapshot_id) throw new Error('No snapshot ID returned from request'); let snapshot_id = trigger_response.data.snapshot_id; console.error(`[web_data_${id}] triggered collection with ` +`snapshot ID: ${snapshot_id}`); let max_attempts = 600; let attempts = 0; while (attempts < max_attempts) { try { if (ctx && ctx.reportProgress) { await ctx.reportProgress({ progress: attempts, total: max_attempts, message: `Polling for data (attempt ` +`${attempts + 1}/${max_attempts})`, }); } let snapshot_response = await axios({ url: `https://api.brightdata.com/datasets/v3` +`/snapshot/${snapshot_id}`, params: {format: 'json'}, method: 'GET', headers: api_headers(), }); if (['running', 'building'].includes(snapshot_response.data?.status)) { console.error(`[web_data_${id}] snapshot not ready, ` +`polling again (attempt ` +`${attempts + 1}/${max_attempts})`); attempts++; await new Promise(resolve=>setTimeout(resolve, 1000)); continue; } console.error(`[web_data_${id}] snapshot data received ` +`after ${attempts + 1} attempts`); let result_data = JSON.stringify(snapshot_response.data); return result_data; } catch(e){ console.error(`[web_data_${id}] polling error: ` +`${e.message}`); attempts++; await new Promise(resolve=>setTimeout(resolve, 1000)); } } throw new Error(`Timeout after ${max_attempts} seconds waiting ` +`for data`); }),
• server.js:296-305 (schema)

  Dataset configuration defining the tool ID, dataset_id, description, input parameters (keyword: string, url: string.url(), pages_to_search: string default '1'), used to generate the Zod schema for web_data_amazon_product_search.
  id: 'amazon_product_search', dataset_id: 'gd_lwdb4vjm1ehb499uxs', description: [ 'Quickly read structured amazon product search data.', 'Requires a valid search keyword and amazon domain URL.', 'This can be a cache lookup, so it can be more reliable than scraping', ].join('\n'), inputs: ['keyword', 'url', 'pages_to_search'], defaults: {pages_to_search: '1'}, }, {
• server.js:674-745 (registration)

  Loop that registers all web_data_* tools, including web_data_amazon_product_search, by constructing name from 'web_data_' + dataset.id, Zod schema from inputs/defaults, description, and shared execute handler.
  for (let {dataset_id, id, description, inputs, defaults = {}} of datasets) { let parameters = {}; for (let input of inputs) { let param_schema = input=='url' ? z.string().url() : z.string(); parameters[input] = defaults[input] !== undefined ? param_schema.default(defaults[input]) : param_schema; } addTool({ name: `web_data_${id}`, description, parameters: z.object(parameters), execute: tool_fn(`web_data_${id}`, async(data, ctx)=>{ let trigger_response = await axios({ url: 'https://api.brightdata.com/datasets/v3/trigger', params: {dataset_id, include_errors: true}, method: 'POST', data: [data], headers: api_headers(), }); if (!trigger_response.data?.snapshot_id) throw new Error('No snapshot ID returned from request'); let snapshot_id = trigger_response.data.snapshot_id; console.error(`[web_data_${id}] triggered collection with ` +`snapshot ID: ${snapshot_id}`); let max_attempts = 600; let attempts = 0; while (attempts < max_attempts) { try { if (ctx && ctx.reportProgress) { await ctx.reportProgress({ progress: attempts, total: max_attempts, message: `Polling for data (attempt ` +`${attempts + 1}/${max_attempts})`, }); } let snapshot_response = await axios({ url: `https://api.brightdata.com/datasets/v3` +`/snapshot/${snapshot_id}`, params: {format: 'json'}, method: 'GET', headers: api_headers(), }); if (['running', 'building'].includes(snapshot_response.data?.status)) { console.error(`[web_data_${id}] snapshot not ready, ` +`polling again (attempt ` +`${attempts + 1}/${max_attempts})`); attempts++; await new Promise(resolve=>setTimeout(resolve, 1000)); continue; } console.error(`[web_data_${id}] snapshot data received ` +`after ${attempts + 1} attempts`); let result_data = JSON.stringify(snapshot_response.data); return result_data; } catch(e){ console.error(`[web_data_${id}] polling error: ` +`${e.message}`); attempts++; await new Promise(resolve=>setTimeout(resolve, 1000)); } } throw new Error(`Timeout after ${max_attempts} seconds waiting ` +`for data`); }), }); }
• server.js:752-778 (helper)

  Helper wrapper around tool execute functions, providing rate limiting, stats tracking, logging, error handling with HTTP details, and timing.
  function tool_fn(name, fn){ return async(data, ctx)=>{ check_rate_limit(); debug_stats.tool_calls[name] = debug_stats.tool_calls[name]||0; debug_stats.tool_calls[name]++; debug_stats.session_calls++; let ts = Date.now(); console.error(`[%s] executing %s`, name, JSON.stringify(data)); try { return await fn(data, ctx); } catch(e){ if (e.response) { console.error(`[%s] error %s %s: %s`, name, e.response.status, e.response.statusText, e.response.data); let message = e.response.data; if (message?.length) throw new Error(`HTTP ${e.response.status}: ${message}`); } else console.error(`[%s] error %s`, name, e.stack); throw e; } finally { let dur = Date.now()-ts; console.error(`[%s] tool finished in %sms`, name, dur); } }; }