- Home
- MCP servers
- Google Search
Google Search
- python
6
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"gradusnikov-google-search-mcp-server": {
"command": "mcp",
"args": [
"run",
"google_search_mcp_server.py"
],
"env": {
"GOOGLE_CSE_ID": "YOUR_CUSTOM_SEARCH_ENGINE_ID",
"GOOGLE_API_KEY": "YOUR_GOOGLE_API_KEY"
}
}
}
}This MCP server lets you perform Google Custom Search queries through a Model Context Protocol endpoint. It enables your agents to search the web via Google and return structured results within your conversations, making it easy to fetch up-to-date information without leaving the chat environment.
How to use
You interact with the Google Custom Search MCP server through an MCP client. Start the server using your chosen run method, then point your client to the local or remote MCP endpoint. When you send a search request, the server queries Google Custom Search using your configured API key and Search Engine ID, and returns results you can parse and display in your application.
How to install
Prerequisites you need before installation:
- Node.js and npm for automatic installation via Smithery
- Python and pip for manual installation
Option 1 — Installing via Smithery (automatic)
npx -y @smithery/cli install @gradusnikov/google-search-mcp-server --client claude
Option 2 — Manual installation
Clone the repository and install dependencies to run the server locally.
git clone https://github.com/gradusnikov/google-search-mpc-server.git
cd google-search-mpc-server
Install Python dependencies required to run the MCP server.
pip install fastmcp google-api-python-client python-dotenv