MCP Glossary

This glossary defines the terms used in our MCP system. If you're new to MCP, you may find it helpful to review this glossary before diving into the more technical details.

MCP

MCP stands for "Model Context Protocol". It is a protocol that allows developers to create custom APIs for AI agents to access autonomously. MCP servers can be used to simple things like expose some data via query parameters, or more advanced features like booking you a flight on your favorite Airline. Learn more about MCP here.

Server

A server that follows the Model Context Protocol specification. MCP servers are responsible for providing ways to gather contextual information for an agent, and for executing actions outside of the Hi.xyz platform.

Client

A client that connects to an MCP server and interacts with it. MCP clients are responsible for sending requests to the MCP server, and for hanlding the responses sent back.

Logic Chain

The MCP Logic Chain is a propreitary feature of the Hi platform that allows your agents to access and use MCP servers in an extremely efficient manner. It mimics real world human thought processes, allowing your agents to feel more natural and engaging. This feature is currently in beta, constantly evolving and improving. Learn more about the MCP Logic Chain here.

Tool

A tool is a function that can be called by an agent. Tools are typically used to create or update data somewhere, like a database or a file. Tools can be used to perform a wide range of tasks, from simple data manipulation to complex AI tasks like image generation or text summarization.

Resource

A resource is a piece of data that can be accessed by an agent. Resources can be anything from a file on a disk, to a query in a database. Resources are typically used to provide data to an agent.