Frequently Asked Questions (FAQ) about Brightsy MCP Server

Q: What is the Brightsy MCP Server? A: The Brightsy MCP Server is a Model Context Protocol (MCP) server that acts as a bridge, connecting your applications to Brightsy AI Agents. It standardizes how your applications provide context to these AI Agents, simplifying integration and enabling seamless communication.

Q: What is MCP (Model Context Protocol)? A: MCP is an open protocol designed to standardize how applications provide context to Large Language Models (LLMs). It ensures consistent communication between applications and AI models, regardless of their underlying architecture.

Q: How do I install the Brightsy MCP Server? A: You can install the server using the following command: npm install.

Q: How do I configure the Brightsy MCP Server? A: You can configure the server by providing your Brightsy Agent ID and API Key. This can be done through command-line arguments (e.g., npm start -- --agent-id=<your-agent-id> --api-key=<your-api-key>) or by setting environment variables (BRIGHTSY_AGENT_ID and BRIGHTSY_API_KEY).

Q: Can I customize the tool name used by the MCP Server? A: Yes, you can customize the tool name using the --tool-name parameter in the command line or by setting the BRIGHTSY_TOOL_NAME environment variable.

Q: How do I test the integration with my Brightsy AI Agent? A: The Brightsy MCP Server includes testing tools. You can run all tests using npm test or specific tests using npm run test:cli (command line interface test) and npm run test:direct (direct MCP protocol test).

Q: What environment variables can be used to configure the server? A: The following environment variables can be used: BRIGHTSY_AGENT_ID (alternative to command-line argument), BRIGHTSY_API_KEY (alternative to command-line argument), and BRIGHTSY_TOOL_NAME (default: “brightsy”).

Q: How does the Brightsy MCP Server work? A: The MCP Server registers a tool with the AI Agent that forwards requests to an OpenAI-compatible AI Agent and returns the response. It takes a messages parameter, which is an array of message objects with role and content properties.

Q: Is the Brightsy MCP Server compatible with UBOS? A: Yes, the Brightsy MCP Server is designed to integrate seamlessly with the UBOS platform, a full-stack AI Agent development platform. UBOS provides tools and services for orchestrating AI Agents, connecting them with enterprise data, and building custom AI Agent systems.

Q: What kind of AI Agents can I use with the Brightsy MCP Server? A: The Brightsy MCP Server is designed to be compatible with OpenAI-compatible AI Agents, giving you flexibility in choosing the right AI model for your needs.