MCP elicitation sends confirmation prompts straight to the user, bypassing the agent
A demo of MCP elicitation shows destructive actions like sending email being confirmed directly by the MCP server in the ChatGPT or Claude client, so the agent never sees or clicks the confirm button.
This is why MCP mogs an API. An agent could send an email to 1000s of people via an API, without you being able to stop it. With MCP elicitation, the agent initiates the call, but NEVER touches the confirmation. It goes straight from the MCP server -> client & you click send. In this example, imagine we tell an agent to send an email to all 2k of our subscribers but notice some info is wrong. We want to cancel it and fix that before it goes out. This is a "destructive" action that a overly proactive agent could do on its own via an API. Even if you sent it a deeplink back to your dashboard it could use computer use or devtools MCP to click the confirm button. With MCP, the agent never sees the confirmation button, it just goes straight to your MCP client (ChatGPT, Claude) and you have to confirm.