Bright Data Web MCP

Instructions

Implementation Reference

• server.js:687-743 (handler)

  The core handler logic for the web_data_crunchbase_company tool. It triggers a BrightData dataset collection using the specific dataset_id and polls the snapshot status until data is ready or times out after 600 attempts.

  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:676-682 (schema)

  Dynamic schema construction for the tool parameters based on the inputs array from the dataset config. For crunchbase_company, inputs=['url'], so parameter 'url' is z.string().url().

  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;
  }

• server.js:409-416 (registration)

  Registration of the dataset configuration for crunchbase_company, which is used in the loop to create the 'web_data_crunchbase_company' tool with name `web_data_${id}`.

      id: 'crunchbase_company',
      dataset_id: 'gd_l1vijqt9jfj7olije',
      description: [
          'Quickly read structured crunchbase company data',
          'This can be a cache lookup, so it can be more reliable than scraping',
      ].join('\n'),
      inputs: ['url'],
  },

• server.js:683-686 (registration)

  The addTool call that registers the web_data_crunchbase_company tool using the dataset config.

  addTool({
      name: `web_data_${id}`,
      description,
      parameters: z.object(parameters),