scrapercity 1.0.14 → 1.0.16

package/AGENT_DOCS.txt

@@ -189,8 +189,11 @@ GET /api/v1/database/leads?title=CTO&country=United States&hasEmail=true&page=1&
   Company filters: keywords (company tags, whole-word, any match), revenueMin, revenueMax (USD),
            companyCountry, companyState, companyCity (company HQ, not the person)
   Exclusions: notTitle, notKeywords, notIndustry
-  apolloUrl=<Apollo people-search URL>: use that search's filters (other params override).
-           The response adds apollo_translation: { applied, approximated, not_supported }.
+  url=<people-search URL>: use that search's filters (other params override).
+           The response adds search_translation: { applied, approximated, not_supported }.
+           A URL with no filters the database can use returns 400.
+  POST /api/v1/database/leads with a JSON body takes the same parameters (arrays as JSON
+           arrays). Use it for a long url or long lists: a query string over ~16KB is refused.
   Country: full name ("United States"); US, USA, UK, UAE also work.
   Array params use repeated keys: ?seniority=vp&seniority=director
   (keywords / notKeywords also accept commas: ?keywords=saas,fintech)
@@ -202,16 +205,24 @@ GET /api/v1/database/leads?title=CTO&country=United States&hasEmail=true&page=1&
   Every lead returned is saved to your account. Only NEW leads count toward the
   100k/day limit; fetching a lead you already have again is free.
   Returns: { data: [...leads], pagination: { page, limit, total, totalPages, has_more, next_after }, rate_limit,
-             apollo_translation? }
+             search_translation? }
   Lead fields include company_industry, company_size, employees_count, company_website,
   company_annual_revenue, company_city, company_state, company_country, keywords.
   409 with filters_not_applied_yet: the company filters listed can't be used yet (company
   data still being prepared right after launch). Nothing is returned or counted; retry later
   or drop those filters.
+  503: the search took too long to run. Narrow it (fewer titles or keywords, add a location
+  or company size) and retry.
+
+GET /api/v1/database/local-businesses?category=Dentist&country=US&hasContact=true&limit=100
+  Local businesses ($149/mo plan and up, 100k new businesses/day), same pattern as above.
+  Filters: category (repeat for several), country (two-letter code), state, city, postalCode,
+  query (business name and description), minRating, maxRating, minReviews, maxReviews,
+  hasEmail, hasPhone, hasWebsite, hasContact (only businesses with a named contact person).
+  Optional: excludeDelivered=true, after=<id> (as above).
 
-GET /api/v1/database/local-businesses?...
 GET /api/v1/database/ecommerce?...
-  Same pattern (including excludeDelivered and after), different datasets.
+  Same pattern (including excludeDelivered and after), different dataset.
 
 ────────────────────────────────────────
 ERROR CODES

package/SKILL.md

@@ -78,8 +78,8 @@ Apollo scrapes take **up to 4 days** to deliver. Do NOT poll in a loop.
 | POST | `/api/v1/scrape/cancel/{runId}` | Cancel running job |
 | GET | `/api/v1/scrape/logs/{runId}` | Run logs |
 | GET | `/api/v1/apollo-status` | Apollo service health: `{status: "url-based" or "legacy", message, timestamp}` |
-| GET | `/api/v1/database/leads?title=CTO&country=United%20States&hasEmail=true&limit=100` | Lead DB ($149/mo plan and up, 100k new leads/day). Optional: `excludeDelivered=true` (only leads you don't have yet), `after=0` then `pagination.next_after` (cursor paging). Company filters: `keywords`, `revenueMin`/`revenueMax`, `companyCountry`/`companyState`/`companyCity`. Exclusions: `notTitle`, `notKeywords`, `notIndustry`. `apolloUrl=<Apollo people-search URL>` searches with that URL's filters |
-| GET | `/api/v1/database/local-businesses?...` | Local biz DB ($149/mo plan and up). Same optional `excludeDelivered` / `after` |
+| GET | `/api/v1/database/leads?title=CTO&country=United%20States&hasEmail=true&limit=100` | Lead DB ($149/mo plan and up, 100k new leads/day). Optional: `excludeDelivered=true` (only leads you don't have yet), `after=0` then `pagination.next_after` (cursor paging). Company filters: `keywords`, `revenueMin`/`revenueMax`, `companyCountry`/`companyState`/`companyCity`. Exclusions: `notTitle`, `notKeywords`, `notIndustry`. `url=<people-search URL>` searches with that URL's filters. POST with a JSON body takes the same parameters (use it for a long `url`) |
+| GET | `/api/v1/database/local-businesses?category=Dentist&country=US&hasContact=true&limit=100` | Local biz DB ($149/mo plan and up, 100k new businesses/day). Filters: `category`, `country`, `state`, `city`, `postalCode`, `query`, `minRating`/`maxRating`, `minReviews`/`maxReviews`, `hasEmail`, `hasPhone`, `hasWebsite`, `hasContact` (only businesses with a named contact person). Same optional `excludeDelivered` / `after` |
 | GET | `/api/v1/database/ecommerce?...` | Ecommerce DB ($149/mo plan and up). Same optional `excludeDelivered` / `after` |
 
 ## Status Values

package/bin/cli.mjs

@@ -376,7 +376,7 @@ async function main() {
                         '--seniority': 'seniority', '--department': 'department',
                         '--page': 'page', '--limit': 'limit',
                         '--min-employees': 'minEmployees', '--max-employees': 'maxEmployees',
-                        '--after': 'after', '--apollo-url': 'apolloUrl',
+                        '--after': 'after', '--url': 'url', '--apollo-url': 'apolloUrl',
                         '--keywords': 'keywords', '--revenue-min': 'revenueMin', '--revenue-max': 'revenueMax',
                         '--company-country': 'companyCountry', '--company-state': 'companyState',
                         '--company-city': 'companyCity', '--not-title': 'notTitle',
@@ -395,7 +395,35 @@ async function main() {
         const r = await sc.dbLeads(params)
         console.log(`${r.pagination?.total || '?'} total leads, page ${r.pagination?.page || 1} of ${r.pagination?.totalPages || '?'}`)
         if (r.pagination?.next_after) console.log(`Next page: --after ${r.pagination.next_after}`)
-        if (r.apollo_translation?.not_supported?.length) console.log(`Not supported from the Apollo URL: ${r.apollo_translation.not_supported.join(', ')}`)
+        const tr = r.search_translation || r.apollo_translation
+        if (tr?.not_supported?.length) console.log(`Not supported from the search URL: ${tr.not_supported.join(', ')}`)
+        console.log(json(r.data?.slice(0, 3) || r))
+        if (r.data?.length > 3) console.log(`... and ${r.data.length - 3} more`)
+        break
+      }
+
+      // ── Database: Local businesses ($149/mo plan and up) ──
+      case 'db-local': {
+        const params = {}
+        const keyFor = { '--category': 'category', '--country': 'country', '--state': 'state', '--city': 'city',
+                        '--postal-code': 'postalCode', '--query': 'query', '--min-rating': 'minRating', '--max-rating': 'maxRating',
+                        '--min-reviews': 'minReviews', '--max-reviews': 'maxReviews', '--page': 'page', '--limit': 'limit',
+                        '--after': 'after' }
+        // List filters take commas: --category "Dentist,Orthodontist" sends both.
+        const lists = new Set(['--category', '--country'])
+        for (const f of Object.keys(keyFor)) {
+          const v = flag(f)
+          if (v === undefined) continue
+          params[keyFor[f]] = lists.has(f) ? String(v).split(',').map(s => s.trim()).filter(Boolean) : v
+        }
+        if (flagBool('--has-email')) params.hasEmail = 'true'
+        if (flagBool('--has-phone')) params.hasPhone = 'true'
+        if (flagBool('--has-website')) params.hasWebsite = 'true'
+        if (flagBool('--has-contact')) params.hasContact = 'true'
+        if (flagBool('--exclude-delivered')) params.excludeDelivered = 'true'
+        const r = await sc.dbLocalBusinesses(params)
+        console.log(`${r.pagination?.total || '?'} total businesses, page ${r.pagination?.page || 1} of ${r.pagination?.totalPages || '?'}`)
+        if (r.pagination?.next_after) console.log(`Next page: --after ${r.pagination.next_after}`)
         console.log(json(r.data?.slice(0, 3) || r))
         if (r.data?.length > 3) console.log(`... and ${r.data.length - 3} more`)
         break
@@ -457,9 +485,15 @@ ScraperCity CLI - B2B lead generation from your terminal
       --min-employees --max-employees --has-email --has-phone
       --keywords --revenue-min --revenue-max --company-country --company-state --company-city
       --not-title --not-keywords --not-industry
-      --apollo-url "<Apollo people-search URL>"  Search with that URL's filters
+      --url "<people-search URL>"  Search with that URL's filters
       --exclude-delivered                    Only leads you don't already have
       --after <id>                           Cursor paging (start with 0, then use the printed next id)
+    scrapercity db-local [filters]           Query local business database
+      --category --country --state --city --postal-code --query
+      --min-rating --max-rating --min-reviews --max-reviews
+      --has-email --has-phone --has-website --has-contact (only businesses with a named contact person)
+      --exclude-delivered                    Only businesses you don't already have
+      --after <id>                           Cursor paging (start with 0, then use the printed next id)
 
   Env: SCRAPERCITY_API_KEY=...  or  scrapercity login
   Docs: https://scrapercity.com/agents

package/bin/mcp.mjs

@@ -50,9 +50,9 @@ const UTILITY_TOOLS = [
   },
   {
     name: 'query_lead_database',
-    description: 'Query the B2B lead database directly. Returns contacts with names, emails, phones, titles, companies (plus company website, revenue, HQ location and keywords). Up to 100 per request. Included with the $149/mo plan (100,000 new leads a day; leads you already have do not count again). For a daily pull of only new leads set excludeDelivered=true. For big pulls page with after: send after="0" first, then the pagination.next_after from each response until it is null. Have an Apollo people-search URL? Pass it as apolloUrl to search with its filters right away (apollo_translation in the response says what was applied).',
+    description: 'Query the B2B lead database directly. Returns contacts with names, emails, phones, titles, companies (plus company website, revenue, HQ location and keywords). Up to 100 per request. Included with the $149/mo plan (100,000 new leads a day; leads you already have do not count again). For a daily pull of only new leads set excludeDelivered=true. For big pulls page with after: send after="0" first, then the pagination.next_after from each response until it is null. Have a saved people-search URL? Pass it as url to search with its filters right away (search_translation in the response says what was applied).',
     inputSchema: { type: 'object', properties: {
-      apolloUrl: { type: 'string', description: 'An Apollo people-search URL (app.apollo.io/#/people?...). Its filters become the search; any other filter you pass overrides the matching one.' },
+      url: { type: 'string', description: 'A people-search URL (the address of a people search with its filters). Its filters become the search; any other filter you pass overrides the matching one.' },
       title: { type: 'string', description: 'Job title filter, comma separated for several (partial match, e.g. "CEO, Founder")' },
       industry: { type: 'array', items: { type: 'string' }, description: 'Company industries (any match)' },
       country: { type: 'array', items: { type: 'string' }, description: 'Person countries, full names like "United States" (US, USA, UK, UAE also work)' },
@@ -81,6 +81,30 @@ const UTILITY_TOOLS = [
       excludeDelivered: { type: 'boolean', description: 'Skip leads this account already has (from the API or unlocked in the dashboard). With this on, keep page at 1 or use after.' },
       after: { type: 'string', description: 'Cursor paging: return leads after this lead id. Use "0" to start, then the pagination.next_after from each response.' }
     } }
+  },
+  {
+    name: 'query_local_business_database',
+    description: 'Query the local business database directly. Returns businesses with phone numbers, emails, websites, addresses and ratings, many with a named contact person. Up to 100 per request. Included with the $149/mo plan (100,000 new businesses a day; businesses you already have do not count again). Set hasContact=true for only businesses with a named contact person. For a daily pull of only new businesses set excludeDelivered=true. For big pulls page with after: send after="0" first, then the pagination.next_after from each response until it is null.',
+    inputSchema: { type: 'object', properties: {
+      category: { type: 'array', items: { type: 'string' }, description: 'Business categories, e.g. ["Dentist"]. A word also finds categories that contain it ("restaurant" finds "Mexican restaurant")' },
+      country: { type: 'array', items: { type: 'string' }, description: 'Two-letter country codes, e.g. ["US"]' },
+      state: { type: 'string', description: 'State or region, comma separated for several (US abbreviations work, e.g. "TX")' },
+      city: { type: 'string', description: 'City (partial match)' },
+      postalCode: { type: 'string', description: 'Postal or zip code' },
+      query: { type: 'string', description: 'Search business names and descriptions' },
+      minRating: { type: 'number', description: 'Minimum Google rating (1-5)' },
+      maxRating: { type: 'number', description: 'Maximum Google rating (1-5)' },
+      minReviews: { type: 'number', description: 'Minimum number of reviews' },
+      maxReviews: { type: 'number', description: 'Maximum number of reviews' },
+      hasEmail: { type: 'boolean', description: 'Only businesses with an email address' },
+      hasPhone: { type: 'boolean', description: 'Only businesses with a phone number' },
+      hasWebsite: { type: 'boolean', description: 'Only businesses with a website' },
+      hasContact: { type: 'boolean', description: 'Only businesses with a named contact person' },
+      page: { type: 'number', description: 'Page number (default 1)', default: 1 },
+      limit: { type: 'number', description: 'Results per page (max 100)', default: 50 },
+      excludeDelivered: { type: 'boolean', description: 'Skip businesses this account already has (from the API or unlocked in the dashboard). With this on, keep page at 1 or use after.' },
+      after: { type: 'string', description: 'Cursor paging: return businesses after this id. Use "0" to start, then the pagination.next_after from each response.' }
+    } }
   }
 ]
 
@@ -116,6 +140,16 @@ server.setRequestHandler(CallToolRequestSchema, async (request) => {
           result = await sc.dbLeads(params)
           break
         }
+        case 'query_local_business_database': {
+          const params = { ...args }
+          for (const k of ['hasEmail', 'hasPhone', 'hasWebsite', 'hasContact', 'excludeDelivered']) {
+            if (params[k]) params[k] = 'true'
+            else delete params[k]
+          }
+          if (params.after !== undefined && params.after !== null) params.after = String(params.after)
+          result = await sc.dbLocalBusinesses(params)
+          break
+        }
         default:
           return { content: [{ type: 'text', text: `Unknown tool: ${name}` }], isError: true }
       }

package/lib/catalog.generated.mjs

@@ -1,6 +1,6 @@
 // AUTO-GENERATED by scripts/generate.mjs — DO NOT EDIT BY HAND.
 // Source of truth: scraperConfigs.ts (+ src/config/scrapers.ts). Regenerate: npm run generate
-// Generated: 2026-10-01T23:44:06.142Z
+// Generated: 2026-10-08T22:24:15.688Z
 export const TOOLS = [
   {
     "name": "scrape_apollo",

package/lib/client.mjs

@@ -166,14 +166,21 @@ export const scrape = (slug, body) =>
 export const postEndpoint = (endpoint, body) => post(endpoint, body)
 
 // ── Databases ($649 plan) ─────────────────────────────────────
+// A long request (a big Apollo URL, a long title or keyword list) goes as a POST with a JSON body:
+// a query string past ~16KB is refused by the server before the search runs.
+const LONG_QUERY = 6000
 export const dbLeads = (params) => {
   const qs = new URLSearchParams()
+  const body = {}
   for (const [k, v] of Object.entries(params)) {
     if (v === undefined || v === null || v === '') continue
     if (Array.isArray(v)) v.forEach(x => qs.append(k, x))
     else qs.append(k, String(v))
+    body[k] = v
   }
-  return get(`${ENDPOINTS['database-leads']}?${qs}`)
+  const qstr = qs.toString()
+  if (qstr.length > LONG_QUERY) return post(ENDPOINTS['database-leads'], body)
+  return get(`${ENDPOINTS['database-leads']}?${qstr}`)
 }
 
 export const dbLocalBusinesses = (params) => {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "scrapercity",
-  "version": "1.0.14",
+  "version": "1.0.16",
   "description": "ScraperCity CLI & MCP Server - B2B lead generation for AI agents",
   "type": "module",
   "bin": {