google-search-mcp-server
A ModelContextProtocol (MCP) server that provides Google Search capabilities as a tool.
Top Comments
The google-search-mcp-server
is an MCP server that offers a google_search
tool for performing web scraping of Google Search results. It returns structured data including titles, URLs, and snippets in a JSON-compatible format. The server supports pagination, configurable language, safe search, and result limits. It also uses random user agents to minimize detection during scraping. The server is designed to handle JSON-RPC requests over standard input/output, making it versatile for integration with various clients.
Features
- Google search scraping via HTTP requests
- Structured JSON output with title, URL, and snippet
- Supports pagination, result limits, and language/country options
- "I'm Feeling Lucky" single-result mode
- Built-in cookie jar and random user-agent for each search
MCP Tools
- google_search: Performs a Google search and returns results in a structured JSON format.
Usage with Different Platforms
Start the MCP Server
bash
npm start
List available tools
bash
echo '{"jsonrpc":"2.0","method":"ListTools","params":{},"id":1}' | npm start
Call the google_search
tool
bash
echo '{"jsonrpc":"2.0","method":"CallTool","params":{"name":"google_search","arguments":{"query":"OpenAI","num":5}},"id":2}' | npm start
Playground
bash
npx esno src/playground.ts
Related MCP Servers
View all browser_automation servers →Fetch
by modelcontextprotocol
Fetch MCP Server is designed to help language models retrieve web content by converting HTML to markdown for easier consumption. It includes features like content truncation, chunk reading, and customizable user-agent settings, making it highly adaptable for various web scraping tasks.