Frequently Asked Questions about UBOS MCP Server

Q: What is an MCP Server? A: MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. UBOS MCP Server provides a robust framework for defining and governing contextual boundaries based on agent roles, ensuring that your AI agents operate within well-defined parameters and deliver reliable, role-specific results.

Q: What are the key features of the UBOS MCP Server? A: Key features include Role Management (creating, updating, deleting roles), Memory Management (role-specific storage, retrieval, TTL), and MCP Integration (exposing roles as resources, providing tools and prompts).

Q: What prerequisites are required to use the UBOS MCP Server? A: You need Node.js 18+ and an OpenAI API key.

Q: How do I install the UBOS MCP Server? A: Clone the repository, install dependencies using npm install, set up the OpenAI API key in a .env file, and build the project using npm run build.

Q: How do I run the UBOS MCP Server? A: Run the server using npm start and the HTTP server for testing using npm run start:http.

Q: How do I configure the UBOS MCP Server? A: Configure the server by modifying src/config.ts. Key configuration options include default roles, tone profiles, memory management settings, and OpenAI model selection.

Q: What are the available resources exposed by the UBOS MCP Server? A: The server exposes role://{roleId} (information about a specific role) and role://tones (available tone profiles).

Q: What tools does the UBOS MCP Server provide? A: The server provides tools for process-with-role, create-role, update-role, delete-role, change-role-tone, store-memory, and clear-role-memories.

Q: What prompts does the UBOS MCP Server provide? A: The server provides prompts for role-{roleId} (use a specific role) and create-custom-role.

Q: How does UBOS enhance AI agent development? A: UBOS provides 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 LLM models, and create Multi-Agent Systems.