Google Search MCP Server
@hunter-arton
关于 Google Search MCP Server
A Google Search MCP server that connects with LLMs or any MCP client to enable realtime search.
基本信息
配置
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"google_search_mcp_server": {
"command": "node",
"args": [
"dist/index.js"
]
}
}
}工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Google Search MCP Server?
A Model Context Protocol (MCP) server that provides web and image search capabilities through Google's Custom Search API. It integrates with Claude and other AI assistants to give them up‑to‑date web and image search abilities.
How to use Google Search MCP Server?
Clone the repository, install dependencies, and build with npm run build. Set up a .env file with GOOGLE_API_KEY and GOOGLE_CSE_ID. Then connect the server to an MCP‑compatible client (Claude for Desktop, VSCode with Claude, or Cursor) by editing the client’s configuration to point to dist/index.js and providing the environment variables.
Key features of Google Search MCP Server
- Two tools:
google_web_searchandgoogle_image_search - Uses Google Custom Search API for real‑time results
- Follows MCP specification for tool‑based interaction
- Communicates via standard input/output transport
- Requires Node.js v18 or higher and Google Cloud credentials
Use cases of Google Search MCP Server
- AI assistant retrieving latest news about a topic
- Finding images related to a query during a conversation
- Getting current information while answering user questions
FAQ from Google Search MCP Server
What tools does this server provide?
It provides google_web_search for web searches and google_image_search for image searches.
What are the prerequisites to run this server?
Node.js v18 or higher, npm, a Google Cloud Platform account, a Custom Search API key, and a Search Engine ID.
How do I set up Google API credentials?
Go to Google Cloud Console, create a project, enable the Custom Search API, and create an API key. Then create a Programmable Search Engine that searches the entire web and copy its Search Engine ID.
How do I connect the server to Claude for Desktop?
Add a google_search entry to claude_desktop_config.json with the command node, the absolute path to dist/index.js, and environment variables for GOOGLE_API_KEY and GOOGLE_CSE_ID.
How can I test the server manually?
Run a JSON‑RPC call via echo '{"jsonrpc":"2.0","method":"callTool","params":{"name":"google_web_search","arguments":{"query":"test"}},"id":1}' | node dist/index.js.
搜索 分类下的更多 MCP 服务器
🚀 OneSearch MCP Server: Web Search & Crawl & Scraper & Extract
yokingma🚀 OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.
Version 2.0 is here!!
mixelpixxMCP Server built for use with Claude Code, Claude Desktop, VS Code, Cline - enable google search and ability to follow links and research websites
Everything Search MCP Server
mamertofabianTavily Mcp
tavily-aiProduction ready MCP server with real-time search, extract, map & crawl.
mcp-omnisearch
spences10🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.
评论