This repository provides a Model Context Protocol (MCP) server offering web search via Google Custom Search API and webpage content extraction. It allows searching the web and extracting text from webpages.
This project provides a Model Context Protocol (MCP) server, enabling web search and webpage reading functionalities. It leverages the Google Custom Search API for web searches and extracts content from webpages.
Setup: Requires a Google Cloud Project with the Custom Search API enabled. You'll need an API key and a Custom Search Engine ID.
Development: Use npm install
for dependencies, npm run build
to build, and npm run watch
for auto-rebuild during development.
Features: Includes a search tool (utilizing the Google Custom Search API) and a webpage reader tool (extracting content from webpages). The search tool allows you to search the web or specific sites, controlling the number of results. The webpage reader extracts the title and main text, cleaning the content.
Installation: Can be installed via Smithery using the provided command. Configuration involves adding the server config to Claude Desktop with your Google API credentials.
Usage: Examples are provided for both the search and webpage reader tools, demonstrating how to structure requests. For debugging, the MCP Inspector is recommended, accessible via npm run inspector
.
adenot/mcp-google-search
February 1, 2025
March 26, 2025
JavaScript