Skip to content

Glossary · Learning platforms

MCP

MCP (Model Context Protocol) is an open standard that lets AI assistants connect to other systems, such as a learning platform, and work in them.

MCP (Model Context Protocol) is an open standard that connects AI assistants to other systems. It was introduced in 2024 and is now supported by the major AI providers. With MCP, an AI assistant can read data from a system and perform tasks in it, not just answer questions about it.

It works through an MCP server. The system, for example a learning platform, exposes a set of tools: create a course, enroll an employee, pull a completion report. The AI assistant calls those tools on the user's behalf, with the user's permissions.

For learning teams, this changes daily work. Instead of clicking through an admin interface, you can ask an AI assistant to draft a course, assign it to a department, and report on completion, and the assistant does it directly in the platform.

When you compare learning platforms, ask whether the platform has an MCP server, what tools it exposes, and how access and permissions are controlled.

Want to see what it looks like in practice?

We show you Skillflow with a course like yours – from the first course to documented completion.