What is an MCP Server?

An MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It standardizes how applications provide context to LLMs.

How does the UBOS MCP Server simplify development?

The UBOS MCP Server uses a declarative approach, allowing you to define what you want the server to do rather than how it should do it, reducing complexity and development time.

What are the key features of the UBOS MCP Server?

Key features include declarative configuration, tool definition, prompt management, and resource management, all designed to streamline AI Agent interactions.

What is the Tool Definition Format?

The Tool Definition Format includes the tool’s name, a parameter schema (defining accepted parameters), a handler function (executing the tool), and an optional description.

What is the Prompt Definition Format?

The Prompt Definition Format includes the prompt’s name, a parameter schema, a handler function (generating the prompt message), and an optional description.

What is the Resource Definition Format?

The Resource Definition Format includes the resource’s URI and a handler function that retrieves the resource content.

How do I connect the MCP server to a transport?

You can connect to a transport by calling the connect() method on the DeclarativeMCPServer instance and passing in the transport object (e.g., HTTP, WebSockets, gRPC).

What is UBOS?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model, and create Multi-Agent Systems.

What is DeclarativeMCPServer?

DeclarativeMCPServer is a utility module for creating Model Context Protocol (MCP) servers declaratively.

What options does DeclarativeMCPServer accept?

DeclarativeMCPServer accepts name, version, tools, prompts, and resources.