ai.mapsdata由 mapsdata.ai 發布官方發布者v1.0.0更新於 Oct 25, 2026
Build lead lists from Google Maps: businesses with emails, phones and websites, US/CA/UK/AU.
MapsData 從 Google 地圖建立含電子郵件、電話與網站的公司名單，涵蓋美加英澳，讓助理啟動、追蹤並下載擷取工作。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/ai.mapsdata%2Fmapsdata/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"mapsdata": {
"type": "http",
"url": "https://mapsdata.ai/mcp"
}
}
}Search Google Maps categories
Search the Google Maps business categories MapsData can scrape. CALL THIS FIRST, before mapsdata_start_scrape: a scrape's query must be one of these exact categories, and a free-text guess like 'plumbing companies' is rejected.
limitquery必填List valid regions
List the exact region names a scrape accepts for a country. Submit them verbatim. Abbreviations like 'TX' are rejected; use the full name.
countryStart a scrape
Start scraping Google Maps businesses and their emails. Returns IMMEDIATELY with a job id; the scrape itself takes 5 minutes to several hours. Before calling this, confirm the category with mapsdata_search_categories and the region with mapsdata_list_regions. Those two mistakes are the overwhelming majority of rejections. This consumes the user's monthly lead allowance. Set dry_run to check a request against every rule without spending anything.
query必填citiesstatescountrydry_runlist_nametotal_limit必填Check a scrape
Get the current state of one scrape. This is an INSTANT SNAPSHOT of a job that runs for minutes to hours. Do NOT call it repeatedly in a loop. The response includes next_action, the suggested next step for the job's current status. MapsData also emails the user when a scrape finishes.
job_id必填List recent scrapes
List this workspace's recent scrapes, newest first.
limitstatusCancel a scrape
Cancel a queued or running scrape. A queued scrape costs nothing. CANCELLING A RUNNING SCRAPE STILL BILLS the leads already delivered, so confirm with the user before calling this.
job_id必填Get a download link
Get a link to a finished scrape's results. The link expires in 15 minutes, so hand it to the user promptly rather than storing it.
scopeformatjob_id必填Check plan usage
How much of this month's lead allowance is left, and the largest single scrape this plan allows. Read max_rows_this_scrape before choosing a total_limit.
無需輸入參數。
已滿足適用檢查項的 83%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
請宣告包含 README 的 GitHub 儲存庫，或在 OAuth 受保護資源後設資料中提供 resource_documentation。
託管服務按其提供方的條款使用，因此這裡不要求授權條款。此檢查項不計入百分比。
