Stop describing UI to your AI agent in words. Alt+click any layer in your running page or Android app and type the change in its chat. Your agent (Claude Code, Codex, Cursor, Copilot…) gets the…
layout-debug-mcp is an MCP project maintained in the antonchuraev99/layout-debug-mcp repository. The maintainer describes its purpose as “Stop describing UI to your AI agent in words. Alt+click any layer in your running page or Android app and type the change in its…”. Read the project documentation for the complete scope.
The documented npm package is layout-debug-mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares LD_TARGET_URL. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-09.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| open_window | Starts the local server if it isn't running, opens the window, and tells the agent to start listening |
| wait_for_message | Waits for the next message or edit from the window and returns it with the element's artifacts. Returns "no message yet" after the timeout, and the agent… |
| reply_in_window | Writes to the window's chat: what changed, which files, what's left. With requestId it closes exactly that request |
| layout_snapshot | Tree of the latest snapshot: nodes, sizes, anchors for finding them in code. Depth-limited |
| selected_element | What the user has selected in the window right now: box, anchors, parent chain, live tweaks |
| pending_requests | All requests sent from the window, for agents that don't listen |
{
"mcpServers": {
"layout-debug": {
"command": "npx",
"args": [
"-y",
"layout-debug-mcp"
],
"env": {
"LD_TARGET_URL": "http://localhost:3000"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| LD_TARGET_URL | Declared in the maintainer’s client configuration. | Check documentation |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.