Frequently Asked Questions (FAQ) about MCP Server on UBOS

Q: What is MCP Server?

A: MCP (Machine Control Protocol) Server provides browser automation capabilities through a simple API. It allows AI models to access and interact with external data sources and tools within a browser environment by translating natural language commands into actions.

Q: What are the prerequisites for using MCP Server?

A: You need Python 3.11+, Poetry for dependency management, and an OpenAI API key.

Q: How do I install the dependencies for MCP Server?

A: Use the command poetry install in the MCP Server directory.

Q: How do I configure the environment variables?

A: Create a .env file in the root directory with the OPENAI_API_KEY variable set to your OpenAI API key.

Q: How do I run the MCP Server?

A: Use the command poetry run python main.py in the MCP Server directory.

Q: What kind of tasks can I automate with MCP Server?

A: You can automate a wide range of tasks, including data extraction, form filling, web testing, social media automation, e-commerce automation, and more.

Q: How does UBOS enhance the functionality of MCP Server?

A: UBOS provides a scalable, reliable, and secure environment for deploying and managing AI agents that utilize MCP Server, offering seamless integration with other UBOS tools and resources.

Q: Can I use my own LLM models with MCP Server on UBOS?

A: Yes, UBOS allows you to build custom AI agents using your own LLM models, tailoring them to your specific business needs when integrated with MCP server.

Q: Where can I obtain the MCP Server for UBOS?

A: You can find the MCP Server on the UBOS Asset Marketplace.

Q: What is FastMCP and how is it used in MCP Server?

A: FastMCP is used for creating a simple, efficient API server that handles requests and responses for the MCP Server.

Q: What does SSE (Server-Sent Events) transport mean?

A: SSE enables real-time communication and feedback between the server and client, facilitating live updates during task execution.