Google Places MCP Server

Google Places MCP Server

Integrates with Google Places API to allow searching, retrieving details, and finding nearby places through an MCP server interface.

Category
访问服务器

README

Google Places MCP Server

This MCP server integrates with Google Places API to allow searching, retrieving details, and finding nearby places.

Setup

Environment Variables

The following environment variables are required:

  • GOOGLE_MAPS_API_KEY: Your Google Maps API key with Places API access enabled
  • TRANSPORT_TYPE: Transport method to use (stdio or sse)
  • PORT: (Optional) Port number for SSE transport (default: 3000)

Create a .env file in the root directory with these variables:

GOOGLE_MAPS_API_KEY=your_api_key_here
PORT=3000

Development

  1. Install dependencies:
npm install
  1. Start the development server:
npm run dev

Transport Options

The server supports two transport methods:

  1. SSE (Server-Sent Events): Uses HTTP with Server-Sent Events for real-time communication

When using SSE transport, the server exposes two endpoints:

  • GET /sse: SSE endpoint for receiving server messages
  • POST /messages: Endpoint for sending messages to the server

Tools

  • [x] places-text-search

    • Text search for places using Google Places API
    • Input:
      • textQuery (string, required): The text query to search for places
      • includedType (string, optional): Restricts results to places matching the specified type
      • includePureServiceAreaBusinesses (boolean, optional): Include businesses without physical location
      • languageCode (string, optional): Language code for results (e.g., "en")
      • locationBias (object, optional): Bias results toward this location
      • locationRestriction (object, optional): Restrict results to this location
      • pageSize (number, optional): Number of results per page (1-20)
      • pageToken (string, optional): Token for next page of results
      • priceLevels (array, optional): Filter by price levels
      • rankPreference (string, optional): Rank by "RELEVANCE" or "DISTANCE"
      • regionCode (string, optional): Two-character country/region code
      • strictTypeFiltering (boolean, optional): Only return exact type matches
      • evOptions (object, optional): EV charging station filters
      • minRating (number, optional): Minimum rating filter (0-5)
      • openNow (boolean, optional): Filter for places currently open
      • fields (array, optional): Specific fields to include in response
    • Returns matching places with details
  • [ ] places-nearby-search (Coming Soon)

    • Find places near a specific location
    • Input:
      • location (object, required): Latitude and longitude coordinates
      • radius (number, optional): Search radius in meters
      • keyword (string, optional): Keyword to filter results
      • type (string, optional): Place type to filter results
      • rankBy (string, optional): Rank by "prominence" or "distance"
      • openNow (boolean, optional): Filter for places that are currently open
      • fields (array, optional): Specific fields to include in the response
    • Returns nearby places with details
  • [ ] place-details (Coming Soon)

    • Get detailed information about a specific place
    • Input:
      • placeId (string, required): Google Place ID
      • fields (array, optional): Specific fields to include in the response
      • languageCode (string, optional): Language code for results
    • Returns comprehensive details about the place
  • [ ] place-photo (Coming Soon)

    • Retrieve photos for a place
    • Input:
      • photoReference (string, required): Reference from a Place Details response
      • maxWidth (number, optional): Maximum width of the returned image
      • maxHeight (number, optional): Maximum height of the returned image
    • Returns photo data or URL

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选