Deploy via MCP

Support for deploying training through MCP (the Model Context Protocol) is coming soon. It will let AI assistants and agents reach your Coassemble courses directly, so the right training can be surfaced inside the AI tools people already work in. This page describes the intended approach and will be updated with exact steps when it ships.

MCP is an open standard for connecting AI assistants and agents to external tools and content. Deploying training through MCP means exposing your Coassemble courses to an AI agent so it can find and serve the right learning in the place a person is already working, rather than them going to a separate portal to look for it.

What this is for

A lot of learning gets missed simply because nobody goes looking for it at the moment they need it. If an AI assistant can reach your training directly, it can bring the right course to someone in the flow of their work, for example when a new starter asks a question, or a customer is stuck on a feature. MCP is the connection that makes that possible without you building a custom integration for each AI tool.

How it's intended to work

The plan is for Coassemble to make your courses available over MCP, so a connected AI assistant or agent can request the right one and deliver it in context. Because MCP is an open standard, this is intended to work across the AI tools that support it rather than being tied to a single assistant.

The exact setup, what's required, and which plans include it will be confirmed when the feature is released. We'll update this page with concrete steps then.

Frequently asked questions

Is this available now?

Not yet. MCP deployment is coming soon. This page will be updated with setup steps and requirements once it's released.

What is MCP?

MCP, the Model Context Protocol, is an open standard for connecting AI assistants and agents to external content and tools. It lets an AI tool reach your training directly rather than through a one-off custom integration.

Which AI tools will this work with?

MCP is an open standard, so the intent is to support the AI assistants and agents that work with it rather than a single tool. Specifics will be confirmed at release.