Frequently Asked Questions (FAQ) about the MCP Framework

Q: What is the Model Context Protocol (MCP)? A: MCP is an open protocol that standardizes how applications provide context to Large Language Models (LLMs), enabling them to access and interact with external data sources and tools.

Q: What is the @ronangrant/mcp-framework? A: It’s a TypeScript framework designed to simplify the creation of Model Context Protocol (MCP) servers. It provides a structured and efficient way to build servers that facilitate communication between AI models and the external world.

Q: What are the key features of the @ronangrant/mcp-framework? A: Key features include automatic discovery of tools, resources, and prompts, TypeScript-first development, built on the official MCP SDK, easy-to-use base classes, multiple transport support (stdio, SSE), and out-of-the-box authentication for SSE endpoints.

Q: How do I install the @ronangrant/mcp-framework? A: You can install it using npm with the command: npm install @ronangrant/mcp-framework

Q: How do I create a new MCP server project? A: You can use the CLI with the command: mcp create <your project name here>

Q: What transport options are supported by the framework? A: The framework supports stdio (default) and sse (Server-Sent Events) transports.

Q: What authentication methods are available for SSE endpoints? A: You can use JWT (JSON Web Token) or API Key authentication, or implement your own custom authentication provider.

Q: How does the framework integrate with UBOS? A: Integrating the @ronangrant/mcp-framework with UBOS allows you to leverage the framework’s capabilities within the UBOS ecosystem, creating a seamless AI agent development experience. UBOS provides tools for orchestration, data connection, custom agent building, and deployment.

Q: Where can I find the full documentation for the framework? A: You can find the full documentation at https://mcp-framework.com

Q: What license is the framework released under? A: The framework is released under the MIT license.