Glossary / MCP
What is MCP?
Model Context Protocol
MCP (Model Context Protocol) is an open standard that lets AI assistants such as Claude, ChatGPT or Cursor connect to outside tools and data, so they can look things up and take actions instead of only chatting.
Without MCP, every AI assistant needed its own custom connection to every service. MCP gives them a shared plug: a service publishes an "MCP server" describing what it can do, and any assistant that speaks MCP can use it.
An MCP server offers tools, such as "search my files", "create an invoice" or "publish this project". When you ask the assistant for something, it decides which tool to call, calls it, and uses the answer in its reply.
For people building apps, MCP means you can work from the assistant you already use. You can ask it to read your database, open a ticket or deploy a change, and it does so through the service's MCP server rather than you copying and pasting between windows.
Mythex has an MCP server, so you can create and change Mythex projects from Claude, Cursor or Codex.
Examples
- Asking Claude to read rows from your app's database
- Asking Cursor to publish a project to a live URL
- Connecting an assistant to your calendar or issue tracker
Questions
Who created MCP?
MCP was introduced by Anthropic as an open standard and is now supported by many AI assistants and developer tools.
Is MCP the same as an API?
No. An API is how one program talks to another. MCP is a standard way of describing tools so that AI assistants can find and use them. An MCP server often calls a service's API behind the scenes.
Is MCP safe to use?
Treat an MCP server like any app you give access to. Connect only servers you trust, check what each tool is allowed to do, and approve actions that change or delete things.