$ loading_
Receive and manage browser UI feedback for coding agents.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "earmark" yet — see the docs or source repo.
Watch for new feedback from the browser overlay. When a user clicks a problematic button, capture the element selector, source path, and computed styles, then organize them into a fix list.
A structured list of button-related feedback with selectors, source locations, and computed style details.
Ask a follow-up question on a UI feedback item: confirm whether the issue only appears on hover, then wait for the browser-side response and update the feedback status.
A follow-up record is created, and the feedback context is updated after a reply is received.
Acknowledge and mark each fixed UI feedback item as resolved. Dismiss invalid or duplicate feedback directly.
Status results showing which feedback items were acknowledged, resolved, or dismissed.
When debugging page styling or interaction issues, developers can use the browser overlay to capture clicked elements, selectors, source paths, and computed styles, reducing manual inspection time.
During page review, designers or product managers can submit UI feedback through the overlay and let coding agents manage it with asking, acknowledging, resolving, or dismissing actions.
It is an MCP server that lets coding agents receive UI feedback from a browser overlay. Feedback can include clicked elements, selectors, source paths, and computed styles, and it can be managed with several tools.
Based on the provided information, it supports tools such as watch, ask, acknowledge, resolve, and dismiss for monitoring, questioning, confirming, resolving, and dismissing feedback.
The provided material does not include installation steps, dependencies, or key requirements. See the source repository for exact prerequisites.
Lets coding agents receive and manage browser UI feedback.
Captures recordings and turns them into timestamped Markdown bug reports.
Give AI coding agents filesystem, Git, database, and compute tools via MCP.
Create feedback-driven AI workflows with user confirmation to reduce risky actions.
Automate browsers to capture web page console logs for debugging and testing.
Point AI to DOM elements for faster frontend debugging and editing.