web_data_crunchbase_company
Extract structured company information from Crunchbase URLs using cached data for reliable access to business profiles and details.
Instructions
Quickly read structured crunchbase company data This can be a cache lookup, so it can be more reliable than scraping
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
Implementation Reference
- server.js:409-416 (registration)Dataset configuration entry that defines the ID 'crunchbase_company', dataset_id, description, and inputs ['url'] used to dynamically generate and register the tool 'web_data_crunchbase_company'.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:676-682 (schema)Dynamic construction of Zod schema for tool parameters based on dataset.inputs. For 'crunchbase_company', produces z.object({url: 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:683-745 (registration)The addTool call within the loop over datasets that registers the tool 'web_data_crunchbase_company' with its name, description, parameters schema, and execute handler.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 ${max_attempts} seconds waiting ` +`for data`); }), }); }
- server.js:687-743 (handler)Core handler logic shared across all web_data_* tools. Triggers dataset collection via BrightData API using the specific dataset_id, polls the snapshot status up to 600 times (10 minutes), and returns the JSON data when ready.execute: tool_fn(`web_data_${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)Utility function that wraps all tool execute handlers, adding rate limiting, stats tracking, logging, error handling with API 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); } }; }