What prerequisites are needed?
Node.js v16 or higher, a Google Cloud Platform account, a Custom Search Engine ID, and a Google API Key.
Version 2.0 is here MCP Server
@MCP-Mirror
基本情報
Version 2.0 is here MCP Server について
Mirror of
Version 2.0 is here MCP Server の設定
Version 2.0 is here MCP Server のツール
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Google Search MCP Server?
An MCP (Model Context Protocol) server that provides Google search capabilities and webpage content analysis tools. It enables AI models to perform Google searches, extract webpage content, and analyze results programmatically.
How to use Google Search MCP Server?
Install Node.js dependencies, build TypeScript, and configure your Google API credentials (GOOGLE_API_KEY, GOOGLE_SEARCH_ENGINE_ID) in the MCP settings file. Start the server with npm run start. Invoke tools like google_search, extract_webpage_content, or extract_multiple_webpages via any MCP client.
Key features of Google Search MCP Server
- Google Custom Search integration with advanced filters and pagination
- Webpage content extraction in Markdown, HTML, or plain text
- Batch analysis of multiple webpages in a single request
- Automatic result categorization and content summarization
- Optimized, human-readable search result responses
- MCP-compliant interface with caching for performance
Use cases of Google Search MCP Server
- Searching the web for current information and returning structured results
- Extracting and summarizing article content from a URL
- Comparing information from multiple sources simultaneously
- Filtering search results by site, language, date, or exact terms
- Paginating through large result sets programmatically
よくある質問
How do I configure the server?
Set environment variables `GOOGLE_API_KEY` and `GOOGLE_SEARCH_ENGINE_ID`, then add the server configuration to your MCP settings file (e.g., `cline_mcp_settings.json`) with the `stdio` transport type.
What tools are available?
Three tools: `google_search` (with optional filters and pagination), `extract_webpage_content` (single URL), and `extract_multiple_webpages` (batch URLs). All support auto-approval in MCP settings.
What happens if my API credentials are invalid?
The server returns detailed error messages for missing or invalid API credentials, failed search requests, invalid URLs, and network connectivity issues.
Where does the data live?
Search results and webpage content are fetched live from Google and the target websites. The server caches responses locally to reduce API calls, but no data is stored permanently.
「検索」の他のコンテンツ
Thordata MCP Server
ThordataThordata MCP Server gives AI agents real-time access to Google, Bing, DuckDuckGo, and Yandex search through one MCP connection. It supports structured results, geo-targeting, language and device parameters, SEO monitorin
Ransack
chancewalker165-dotEvery SERP, every extractor. One MCP: search, page fetch, cited research, transcripts, product prices and permit records for AI agents, with the source URL on every result.
CUQU找搭子 MCP（粗趣）
cuqu-netCUQU找搭子官方 Agent Skill：让任意 AI Agent（Claude Code/Codex/Cursor/WorkBuddy）代用户找同城线下局、报名、支付、发局。MCP Streamable HTTP + 个人 API Key 网关 agent.cuqu.net
Sorank
Thibault Besson-MagdelainSorank connects Google Search Console, PageSpeed Insights, and AI citability scoring to your assistant, so it can diagnose why a page underperforms and tell you exactly what to change. Sorank gives your AI assistant dir
S
SaaS Think Tank — Software Research
SaaS Think TankSoftware research to help people choose the right tools. SaaS Think Tank publishes software comparisons, reviews and practical resources across categories, with dated findings, source links and clear limits. Current MCP
コメント