---
title: "Comment by Kartik N V J K on \"We gave our MCP server an undo button\" | Hashnode"
description: "Making the preview the real undo, rolled back, is the line I'm taking with me. A separate preview path would drift from the real one sooner or later. My worry i"
url: "https://hashnode.com/posts/we-gave-our-mcp-server-an-undo-button/6ad836b459e12396314dd304/comment/6ad9f6c433fb0a7d0ff0dbab"
---

[Discussion](https://hashnode.com/posts/we-gave-our-mcp-server-an-undo-button/6ad836b459e12396314dd304)

Comment [We gave our MCP server an undo button](https://hashnode.com/posts/we-gave-our-mcp-server-an-undo-button/6ad836b459e12396314dd304)

[Kartik N V J K](https://hashnode.com/@kartik-nvj)

[Oct 22](https://hashnode.com/posts/we-gave-our-mcp-server-an-undo-button/6ad836b459e12396314dd304/comment/6ad9f6c433fb0a7d0ff0dbab)

Making the preview the real undo, rolled back, is the line I'm taking with me. A separate preview path would drift from the real one sooner or later. My worry is from the agent side: if someone undoes a run mid-session, the agent still believes its funnel exists. When its next write gets refused for joining an undone run, does the error say why, so it doesn't just open a fresh run and put everything back?

[Quentin Wendegass](https://hashnode.com/@quentinw)

[Oct 25](https://hashnode.com/posts/we-gave-our-mcp-server-an-undo-button/6ad836b459e12396314dd304/comment/6ad9f6c433fb0a7d0ff0dbab#reply-6adde2f24c3bcf1186999326)

It says why, but not quite enough. The write gets a 409 with its own error code and "this setup run has been undone and takes no more changes; start a new one". So the agent knows the run is gone, but the message actually nudges it towards a fresh run, and nothing tells it the user undid those changes on purpose. I'll change it to say what was undone and to check with the user before redoing any of it. Thanks, that's a real gap.