Frequently Asked Questions (FAQ) - Memory Store MCP Server

Q: What is an MCP Server? A: MCP stands for Model Context Protocol. An MCP server acts as a bridge, enabling AI models to access and interact with external data sources and tools, providing them with real-time context.

Q: What does the Memory Store MCP Server do? A: It provides web search capabilities to LLMs (Large Language Models) using Google via Puppeteer, returning results in a structured JSON format.

Q: What are the key features of this MCP Server? A: Key features include web search functionality via Google, structured JSON results, a lightweight and stateless design, and easy integration with MCP-enabled systems.

Q: How do I install the Memory Store MCP Server? A: Clone the repository, install dependencies using npm install, and build the project using npm run build.

Q: How do I configure the Memory Store MCP Server? A: Create a .env file in the project root with environment variables such as PUPPETEER_EXECUTABLE_PATH, PUPPETEER_HEADLESS, and PORT.

Q: How do I use the Memory Store MCP Server? A: Start the server using npm start and send MCP requests with the search_web tool and a query.

Q: Can I customize the Memory Store MCP Server? A: Yes, the code is open source and customizable. You can integrate with different search engines, customize search parameters, and implement data filtering.

Q: What is Puppeteer, and why is it used? A: Puppeteer is a Node library that provides a high-level API to control Chrome or Chromium programmatically. It’s used to perform web searches on Google and retrieve the results.

Q: What kind of queries can I perform? A: You can perform any query that you would normally perform on Google. The MCP Server will return the results in a structured JSON format.

Q: What is UBOS? A: UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps orchestrate AI Agents, connect them with enterprise data, build custom AI Agents with custom LLM models, and create Multi-Agent Systems.

Q: How does the Memory Store MCP Server fit into the UBOS ecosystem? A: The Memory Store MCP Server is an asset available on the UBOS Asset Marketplace, providing web search capabilities to AI Agents developed and managed on the UBOS platform.

Q: What license is the Memory Store MCP Server released under? A: This project is licensed under the MIT License. See the LICENSE file for details.

Q: Where can I find more information about the Model Context Protocol (MCP)? A: You can find more information about MCP in the official documentation and community forums related to LLM and AI Agent development.