locationlists.com

No connector needed: any AI assistant can answer a location question by opening https://locationlists.com/find?q=<the question in plain words> — counts, a preview, a price and a card checkout link. Connect the MCP for repeat use or wallet payments. LocationLists sells ready-to-use CSV datasets of US (and some Canadian) business locations — every dealer, store, nonprofit, bank branch or contractor a source publishes. NO SETUP NEEDED: every question these tools answer also has a plain web link that any assistant able to open a page can use, with no connector, account or key: https://locationlists.com/find?dataset=<slug>&near=<place or zip>&radius=<miles> (or drive=<minutes>; state=, city=, zip=, where=<column>:<op>:<value>; category= or datasets= to combine lists; total=<rows>). It returns the count, up to 3 fixed sample rows of the lists involved, the price and a Buy link. A connector is never required to get an answer; a one-off question works from the /find link. When a question is genuinely ambiguous the /find answer (and the JSON's `clarification` field) still carries the best-guess answer, plus a few complete links that each settle one reading: ask your user which they meant, or proceed on the best guess. FREE tools: search_datasets to find datasets (by brand, kind of business or industry), get_dataset for the full record and its filterable columns, get_sample for real rows, and count_locations to count rows matching filters on any column — revenue, employees, category, dealer tier, not just geography — with the exact price of the matching rows. Link twins: search_datasets = https://locationlists.com/find?search=<words>; get_dataset = https://locationlists.com/data/<slug>/dataset.json; count_locations and get_sample = https://locationlists.com/find?dataset=<slug>&<filters>. relate_locations compares two lists by distance (link twin: https://locationlists.com/find?dataset=<slug>&relate=nearest&k=1&b.dataset=<other slug>). count_by_area counts places per county, ZIP, state or metro for up to 4 lists, with has / lacks (link twin: https://locationlists.com/find?areas=county&dataset=<slug>&b.dataset=<other slug>&has=a&lacks=b). Both are free. Every result starts with `answer` (and often `next`): plain words and a link, written for a business reader. The `technicalDetails` field carries tool names, arguments and payment terms for developers and AI agents; anyone may read it. AUTONOMOUS PURCHASE (no account, no human): paid tools settle in USDC on Base via x402. Call count_locations first for the exact cost. query_locations returns the matching rows, priced per row (every match by default); buy_dataset buys the whole file and returns a permanent CSV download link. Calling a paid tool without payment returns a tool result with isError:true whose structuredContent is the x402 PaymentRequired (exact amount, payTo, asset); retry the same call with the signed PaymentPayload in params._meta["x402/payment"]. Failed or empty calls cost nothing. GEOGRAPHY: filter by radius, city or zip (or drive time) with count_locations and get_sample before buying — e.g. near {place: "Los Angeles, CA", radius_miles: 25} or near {place: "Richmond, VA", drive_minutes: 30} on a list with map coordinates (search results say distanceSearch), or city/state/zip, or `where` on any column. count_locations gives the exact number of matches; get_sample with the same filters returns that count plus the list's fixed free sample rows, each marked `matches_your_question` — the same rows whatever the filter, so they show the real column shape, not a sample of the matches. Both are free, and both return `next`, which says how to get every matching row. Each brand or chain is its own dataset. To cover a kind of business near one place ("200 restaurants near Chicago"), pass category (a kind of business, an industry, or "retail") or datasets (a list of slugs) and total instead of dataset: count_locations and get_sample then give one combined answer (counts per dataset, duplicates removed, a preview, one price), and `next` says how to get the rows as one file. Link twins for the same questions: https://locationlists.com/find?dataset=<slug>&near=Los+Angeles+CA&radius=25, https://locationlists.com/find?dataset=<slug>&near=23219&drive=30, https://locationlists.com/find?category=retail&near=Los+Angeles+CA&radius=25&total=100. HUMAN PURCHASE: get_quote prices one or more datasets, create_checkout returns a Stripe payment link to give the user (card, Apple Pay, Google Pay), create_query_checkout returns a card payment link for just the rows matching a filter, and check_order confirms payment and returns the download link. Link twins: create_query_checkout = https://locationlists.com/find/buy?<the same parameters as /find>; create_checkout = https://locationlists.com/data/<slug>/buy; get_quote = the price in any /find answer. List prices are one-time ($9–$199 per dataset by record count). Never claim a dataset is fresher than its lastModified date. If nothing fits what the user wants, offer request_list: ask before sending, and ask for their email so we can tell them when the list is ready (never invent one). email_quote sends the user a quote for exactly their request, with a card checkout link, once they give their email. send_feedback passes a problem or suggestion to the LocationLists team. email_quote's link twin: https://locationlists.com/find/quote?<the same parameters as /find>. request_list's: the "Request it" box at https://locationlists.com after a search.