SerpApi MCP Server
Enables searches across multiple search engines (Google, Bing, YouTube, etc.) and retrieval of parsed search results through SerpApi, allowing natural language queries to access live search engine data.
README
SerpApi MCP Server
Build an MCP server that:
- Get parsed search engines results pages via SerpApi using an API key, fast
This MCP (Model Context Protocol) server integrates with SerpApi to perform searches across various search engines and retrieve both live and archived results. It exposes tools and resources for seamless interaction with MCP clients or hosts, such as Grok or Claude for Desktop.
Installation
To set up the SerpApi MCP server, install the required Python libraries:
pip install mcp serpapi python-dotenv
You’ll also need a SerpApi API key. Sign up at SerpApi to get one.
Quick Start
-
Save the Server Code: Place the server code in a file, e.g., server.py.
-
Configure the API Key: Create a .env file in the same directory with your SerpApi API key:
SERPAPI_API_KEY=your_api_key_here
- Run the Server: Start the server with:
python server.py
- Integrate with an MCP Client: Connect the server to an MCP client or host (e.g., Claude for Desktop). For Claude, update Claude_desktop_config.json:
{
"mcpServers": {
"serpapi": {
"command": "python",
"args": ["path/to/server.py"]
}
}
}
Restart the client to load the server.
Features
-
Supported Engines: Google, Google Light, Bing, Walmart, Yahoo, eBay, YouTube, DuckDuckGo, Yandex, Baidu
-
Tools:
- search: Perform a search on a specified engine with a query and optional parameters.
- Resources:
- locations: Find Google Locations.
Usage Examples
These examples assume an MCP client (e.g., written in Python using the MCP client SDK) is connected to the server. Listing Supported Engines Retrieve the list of supported search engines:
engines = await session.read_resource("locations")
print(engines)
Performing a Search Search for "coffee" on Google with a location filter:
result = await session.call_tool("search", {
"query": "coffee",
"engine": "google",
"location": "Austin, TX"
})
print(result)
Configuration
API Key: Set your SerpApi API key in the .env file as SERPAPI_API_KEY.
Running the Server
Production Mode: Launch the server with:
python server.py
Development Mode: Use the MCP Inspector for debugging:
mcp dev server.py
Testing
Test the server using the MCP Inspector or an MCP client. For Claude for Desktop, configure the server in Claude_desktop_config.json, restart the app, and use the hammer icon to explore and test available tools.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。