Google Programmable Search Engine (PSE) MCP Server

Name: Google Programmable Search Engine (PSE) MCP Server
Author: rendyfebry

@rendyfebry

代码仓库

关于 Google Programmable Search Engine (PSE) MCP Server

A Model Context Protocol (MCP) server for the Google Programmable Search Engine (PSE) API

基本信息

分类

搜索

许可证

Apache-2.0

运行时

node

传输方式

stdio

发布者

rendyfebry

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-pse-mcp": {
      "disabled": false,
      "timeout": 60,
      "command": "npx",
      "args": [
        "-y",
        "google-pse-mcp",
        "https://www.googleapis.com/customsearch",
        "<api_key>",
        "<cx>",
        "<siteRestricted>"
      ],
      "transportType": "stdio"
    }
  }
}

工具

`q` (string, required): Search query

概览

What is Google Programmable Search Engine (PSE) MCP Server?

A Model Context Protocol (MCP) server for the Google Programmable Search Engine (PSE) API. It exposes a search tool that lets MCP-compatible clients (such as VS Code, Copilot, and Claude Desktop) perform web searches using Google Custom Search.

How to use Google Programmable Search Engine (PSE) MCP Server?

No manual cloning or installation is needed. Add the configuration snippet to your MCP client’s settings (e.g., VS Code’s settings.json or Cline’s cline_mcp_settings.json), replacing <api_key> and <cx> with your Google API key and custom search engine ID. An optional <siteRestricted> flag (true/false) controls the endpoint used.

Key features of Google Programmable Search Engine (PSE) MCP Server

Single search tool with rich parameter support
Configurable result size (1–10 per page)
Language and safe search filtering
Optional site‑restricted API endpoint
Works with any stdio‑based MCP client

Use cases of Google Programmable Search Engine (PSE) MCP Server

Perform targeted web searches from within an AI‑powered coding assistant
Integrate Google Custom Search results into automated research workflows
Build custom search experiences limited to specific sites (via siteRestricted)

FAQ from Google Programmable Search Engine (PSE) MCP Server

What credentials do I need?

You need a Google API key and a Custom Search Engine ID (cx). Both are available from the Google Cloud Console.

How does the `siteRestricted` flag work?

It determines whether the server uses the Site‑Restricted API endpoint or the standard Custom Search endpoint. The default value (true) uses the restricted endpoint; set it to false to use the standard endpoint.

What parameters does the `search` tool accept?

Required: q (query). Optional: page (number), size (1–10), sort (only "date"), safe (boolean), lr (language code), and siteRestricted (boolean).

What runtime does the server require?

The server runs via npx (Node.js package runner). No separate installation steps are needed.

Which transport does it use?

The server communicates over stdio, which is the default transport for MCP servers.

搜索分类下的更多 MCP 服务器

Baidu AI Search

baidubce

appbuilder-sdk, 千帆AppBuilder-SDK帮助开发者灵活、快速的搭建AI原生应用

583

duckduckgo-search MCP Server

zhsama

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.

332