Google Search MCP Integration Guide
MCP (Model Context Protocol) is a model context protocol launched by Anthropic that allows AI models (such as Claude, GPT, etc.) to call external tools through standardized interfaces. With the SERP MCP Server provided by 费思量-API, you can directly perform Google searches in AI clients like Claude Desktop, VS Code, Cursor, etc., to obtain search results for web pages, images, news, videos, locations, and more.
¶ Feature Overview
The SERP MCP Server provides the following core functionalities:
- Web Search — Search Google web results
- Image Search — Search Google images
- News Search — Search Google news
- Video Search — Search Google videos
- Location Search — Search Google location information
- Map Search — Search Google maps
- Multilingual and Multiregional — Supports custom country and language parameters
- Time Range Filtering — Filter results by day, week, month, year
¶ Prerequisites
Before use, you need to obtain an 费思量-API API Token:
- Register or log in to the 费思量-API platform
- Go to the Google SERP API page
- Click "Acquire" to get the API Token (first-time applicants receive free credits)
¶ Installation Configuration
¶ Method 1: pip Installation (Recommended)
pip install mcp-serp
¶ Method 2: Source Installation
git clone https://github.com/AceDataCloud/SerpMCP.git
cd SerpMCP
pip install -e .
Once the installation is complete, you can use the mcp-serp command to start the service.
¶ Using in Claude Desktop
Edit the Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add the following configuration:
{
"mcpServers": {
"serp": {
"command": "mcp-serp",
"env": {
"ACEDATACLOUD_API_TOKEN": "Your API Token"
}
}
}
}
If using uvx (no need to install the package in advance):
{
"mcpServers": {
"serp": {
"command": "uvx",
"args": ["mcp-serp"],
"env": {
"ACEDATACLOUD_API_TOKEN": "Your API Token"
}
}
}
}
After saving the configuration, restart Claude Desktop to use the Google search-related tools in the conversation.
¶ Using in VS Code / Cursor
Create a .vscode/mcp.json in the project root directory:
{
"servers": {
"serp": {
"command": "mcp-serp",
"env": {
"ACEDATACLOUD_API_TOKEN": "Your API Token"
}
}
}
}
Or use uvx:
{
"servers": {
"serp": {
"command": "uvx",
"args": ["mcp-serp"],
"env": {
"ACEDATACLOUD_API_TOKEN": "Your API Token"
}
}
}
}
¶ Available Tools List
| Tool Name | Description |
|---|---|
serp_google_search |
Google web search |
serp_google_images |
Google image search |
serp_google_news |
Google news search |
serp_google_videos |
Google video search |
serp_google_places |
Google location search |
serp_google_maps |
Google map search |
¶ Usage Examples
After configuration, you can directly call these functions in the AI client using natural language, for example:
- "Help me search for the latest AI papers"
- "Search for good hotpot restaurants in Beijing"
- "Find images about Python asynchronous programming"
- "Search for today's tech news"
- "Find nearby cafes on the map"
¶ More Information
- GitHub Repository: 费思量-API/SerpMCP
- PyPI Package: mcp-serp
- API Documentation: Search Engine API