Frequently Asked Questions about the Google PSE MCP Server
Q: What is an MCP Server? A: MCP stands for Model Context Protocol. An MCP server standardizes how applications provide context to LLMs, allowing AI models to access and interact with external data sources and tools.
Q: What is the Google Programmable Search Engine (PSE) MCP Server? A: The Google PSE MCP Server is a Model Context Protocol server specifically designed for the Google Programmable Search Engine API. It enables AI agents to search the web using Google Custom Search.
Q: What are the benefits of using the Google PSE MCP Server? A: The key benefits include enhanced interoperability, simplified integration of web search into AI models, improved maintainability of AI applications, and increased scalability for handling web search requests.
Q: What is UBOS? A: UBOS is a Full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. Our platform helps you orchestrate AI Agents, connect them with your enterprise data, and build custom AI Agents with your own LLM model and Multi-Agent Systems.
Q: How do I install the Google PSE MCP Server?
A: You don’t need to manually clone the repository or run installation commands. Simply add the provided configuration to your MCP client (VSCode, Copilot, Cline), replacing <api_key> and <cx> with your Google PSE credentials.
Q: What MCP clients are supported? A: The Google PSE MCP Server is compatible with MCP-compatible clients such as VSCode, Copilot, and Cline.
Q: What tool does this MCP server provide?
A: This MCP server provides the search tool, which allows you to search the web with Google Programmable Search Engine.
Q: What parameters can I use with the search tool?
A: You can use the following parameters:
* q (string, required): Search query
* page (integer, optional): Page number
* size (integer, optional): Number of search results to return per page (1-10)
* sort (string, optional): Sort expression (only ‘date’ is supported)
* safe (boolean, optional): Enable safe search filtering
* lr (string, optional): Restrict search to a particular language (e.g., lang_en)
* siteRestricted (boolean, optional): Use the Site Restricted API endpoint
Q: Where do I find my API key and CX (Custom Search Engine ID)? A: You can obtain your API key and CX from the Google Cloud Console after setting up a Google Programmable Search Engine.
Q: Can I restrict the search to specific websites?
A: Yes, you can use the siteRestricted parameter to restrict the search to a particular website or set of websites.
Q: How does the Google PSE MCP Server integrate with UBOS? A: The Google PSE MCP Server seamlessly integrates with the UBOS platform, allowing you to easily incorporate web search capabilities into your AI agents within the UBOS environment. UBOS provides tools for managing, orchestrating, and connecting AI Agents with enterprise data and custom LLMs.
Q: Is the Google PSE MCP Server secure? A: Yes, the server supports secure authentication using API keys, ensuring that only authorized users can access the search functionality.
Google Programmable Search Engine Server
Project Details
- rendyfebry/google-pse-mcp
- Apache License 2.0
- Last Updated: 5/30/2025
Recomended MCP Servers
MCP server for getting github trending repos & developers
misonote markdown mcp client
MCP server for apple notes
Starter files, final projects, and FAQ for my Ultimate React course
✍ WeChat Markdown Editor | 一款高度简洁的微信 Markdown 编辑器:支持 Markdown 语法、色盘取色、多图上传、一键下载文档、自定义 CSS 样式、一键重置等特性
MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
A type-safe solution to remote MCP communication, enabling effortless integration for centralized management of Model Context.
MCP Server to wrap the FDIC Bank Find API
MCP Implementation for HubSpot
Experimental - Model Context Protocol (MCP) server for the Nylas API





