ai.mapsdata由 mapsdata.ai 发布官方发布者v1.0.0更新于 Oct 25, 2026
Build lead lists from Google Maps: businesses with emails, phones and websites, US/CA/UK/AU.
MapsData 从 Google Maps 构建含邮箱、电话和网站的企业线索名单，覆盖美加英澳，让助手启动、跟踪并下载抓取任务。
Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/ai.mapsdata%2Fmapsdata/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。把它添加到你客户端的 mcpServers 配置中。
{
"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.
无需输入参数。
已满足适用检查项的 83%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
请声明包含 README 的 GitHub 仓库，或在 OAuth 受保护资源元数据中提供 resource_documentation。
托管服务按其提供方的条款使用，因此这里不要求许可证。此检查项不计入百分比。
