scrapercity-cli
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCRAPERCITY_API_KEY | Yes | Your ScraperCity API key, which can be obtained from the ScraperCity dashboard. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_walletA | Check account balance, plan, and billing info. Call this FIRST to verify credits before running any scrape. |
| list_runsA | List recent scraper runs with status, lead counts, and costs. |
| scrape_apolloA | Scrape leads from Apollo.io using a search URL. IMPORTANT: Apollo delivery takes 11-48+ hours. Use webhooks (configure at app.scrapercity.com/dashboard/webhooks) instead of polling. Returns a runId to check status later. |
| scrape_apollo_filtersA | Scrape leads from Apollo.io using filter parameters instead of a URL. Same 4-day delivery - use webhooks. At least one filter required. |
| scrape_mapsA | Scrape businesses from Google Maps. Returns businesses with names, addresses, phone numbers, websites, emails, ratings. Typically completes in 5-30 minutes. |
| validate_emailsA | Validate a list of email addresses. Returns deliverability status, catch-all detection, MX records, and company info. Typically completes in 1-10 minutes. |
| find_emailsB | Find business email addresses given a person name and company. Provide first/last name + domain or company name. |
| find_mobilesB | Find mobile phone numbers from LinkedIn URLs or work emails. |
| find_peopleB | Skip trace / people finder. Look up personal info by name, email, phone, or address. |
| scrape_store_leadsA | Get ecommerce store data (Shopify, WooCommerce, etc). Returns domains, emails, phones, social profiles, revenue estimates. Instant results from cached database. |
| scrape_builtwithB | Find all websites using a specific technology. Returns domains with contact info. $4.99 per search. |
| search_criminal_recordsA | Search criminal records by name. $1 per search, only charged if records found. |
| scrape_airbnbB | Scrape Airbnb host emails by city or listing URL. Returns host contact info including email addresses. |
| scrape_youtube_emailB | Find business emails for YouTube channels. Pass channel handles (@ChannelName) or URLs. |
| scrape_website_finderC | Find contact info (emails, phones, social links) from a list of website domains. Optionally filter by job title. |
| scrape_yelpB | Scrape business listings from Yelp. Search by keyword + location, or provide direct Yelp URLs. |
| scrape_angiB | Scrape service provider listings from Angi (Angie's List). Search by keyword and zip codes. |
| scrape_zillow_agentsC | Scrape real estate agent listings from Zillow by location. |
| scrape_bizbuysellC | Scrape business-for-sale listings from BizBuySell. Provide search result URLs. |
| scrape_crexiA | Scrape commercial real estate listings from Crexi. Provide search result URLs. |
| scrape_property_lookupB | Look up property data by address. Optionally include owner contact information. $0.15 per address. |
| check_run_statusA | Check the status of a scraper run. Returns status (RUNNING/SUCCEEDED/FAILED/CANCELLED), lead count, and download URL when complete. |
| download_resultsA | Download the CSV results of a completed scraper run. Only works when status is SUCCEEDED. |
| cancel_runB | Cancel a running scraper job. |
| query_lead_databaseA | Query the B2B lead database directly (requires $649/mo plan). Returns contacts with names, emails, phones, titles, companies. 100 per request, paginate with page param. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 25 tools
Most tools target distinct sources or specific data types (e.g., scrape_airbnb vs scrape_yelp), and find_* tools are separated from scrape_* tools. However, scrape_apollo and scrape_apollo_filters are very similar, and multiple tools return contact info (find_emails, query_lead_database, scrape_apollo), which could cause misselection.
Tool names follow a clear pattern with verbs like scrape_, find_, check_, search_, etc. The pattern is consistent per category (e.g., all scraping tools use scrape_), but verbs vary across categories. No mixing of naming conventions, and names are readable.
25 tools is on the high side for a single server, but the domain (multi-source scraping and data enrichment) is broad enough to justify many specialized endpoints. Still, some tools could potentially be combined (e.g., scrape_apollo and scrape_apollo_filters).
The tool set covers the full lifecycle of scraping runs (cancel, check, download, list) and provides a wide range of data sources (real estate, business listings, people search, email validation). Minor gaps: no generic web scraper or tool to manage account settings beyond check_wallet.