Perform web searches using Google Custom Search API
Extract and parse content from any webpage
Google Search provides a powerful interface to search the web and extract content from webpages using Google's Custom Search API. It enables AI assistants to perform targeted web searches and retrieve up-to-date information from across the internet. With this tool, you can search the entire web or specific sites, control the number of results returned, and get structured data with titles, links, and snippets. Additionally, the webpage reader functionality allows for extracting and parsing content from any webpage, making it easier to analyze and process web information.
Google Search MCP Server provides web search capabilities using Google Custom Search API and webpage content extraction functionality. This tool enables AI assistants to search the web for up-to-date information and extract content from specific webpages.
Before using this MCP server, you'll need to set up Google API credentials:
Create a Google Cloud Project:
Enable Custom Search API:
Get API Key:
Create Custom Search Engine:
The easiest way to install the Google Search MCP server is via Smithery:
npx -y @smithery/cli install @adenot/mcp-google-search --client claude
Install the package:
npm install -g @adenot/mcp-google-search
Configure your AI assistant client to use the MCP server.
To use with Claude Desktop, add the server configuration with your Google API credentials:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"google-search": {
"command": "npx",
"args": [
"-y",
"@adenot/mcp-google-search"
],
"env": {
"GOOGLE_API_KEY": "your-api-key-here",
"GOOGLE_SEARCH_ENGINE_ID": "your-search-engine-id-here"
}
}
}
}
Since MCP servers communicate over stdio, debugging can be challenging. You can use the MCP Inspector for debugging:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.