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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.