Layout-debug-mcpSAFE
Point at a layer in a live UI (web DOM, Android Compose), drag it on the real screen, hand it to your AI agent via MCP
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/AntonChuraev99/Layout-debug-mcp/releases) [](https://www.npmjs.com/package/layout-debug-mcp) [](./LICENSE) [](https://nodejs.org) [](#roadmap)
Point at the element. Tell your agent what to change.
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 element's anchors, box and parents over MCP, edits the code and answers in the same chat while the frame refreshes with the result.
Need it 16 px lower? Drag it on the real screen first; the measured delta goes along.
[](https://cursor.com/en/install-mcp?name=layout-debug&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsImxheW91dC1kZWJ1Zy1tY3AiXX0%3D) [](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522layout-debug%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522-y%2522%252C%2522layout-debug-mcp%2522%255D%257D) [](https://insiders.vscode.dev/redirect?url=vscode-insiders%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522layout-debug%2522%252C%2522command%2522%253A%2522npx%2522%252C%2522args%2522%253A%255B%2522-y%2522%252C%2522layout-deb
dfa76f46a244OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add layout-debug-mcp -- npx -y [email protected]
Exposed tools (6)
6 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
layout_snapshot | read | |
open_window | read | |
pending_requests | read | |
reply_in_window | read | |
selected_element | read | |
wait_for_message | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (10)
for (const rel of ['../secret.txt', 'assets/../../x', '%2e%2e/x', '..%2fx', 'a/%2E%2E/%2E%2E/x']) {const html = readFileSync(new URL('../../index.html', import.meta.url), 'utf8')import type { EditRequest, LayoutNode, Snapshot } from '../../src/shared/protocol.ts'- The window's dev server listens on `127.0.0.1`; the window URL is `http://127.0.0.1:<LD_UI_PORT>` (`localhost` still works).
| `npm run dev` | Everything for local development, demo page at http://127.0.0.1:5174 |
The window runs on `http://127.0.0.1:5175`. Started by `open_window`, it stops by itself after 30 minutes with no window and no agent. Prefer to start it yourself? `npx layout-debug-mcp window` runs i
<script src="http://127.0.0.1:5175/inspector.js"></script>
| `LD_SERVER_URL` | none | `http://127.0.0.1:5175` | Where the MCP process finds the server (overrides `LD_SERVER_PORT` there) |
@modelcontextprotocol/sdk, ws, zod, @playwright/test, @types/node, @types/react, @types/react-dom, @types/ws
.github/media/hero.gif
Gates applied: no_behavioural_pass.
dfa76f46a244full audit observations/trust-audit/mcp-server/antonchuraev99__layout-debug-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | dfa76f46a244 | SAFE | B | 89 | first audit |
Questions
What is the Layout-debug-mcp MCP server?
Point at a layer in a live UI (web DOM, Android Compose), drag it on the real screen, hand it to your AI agent via MCP
What tools does Layout-debug-mcp expose?
6 in total: 6 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Layout-debug-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Layout-debug-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does Layout-debug-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as layout-debug-mcp at 0.2.0.
How current is this page?
The grade is for one exact copy of the source (dfa76f46a244), read on 2026-10-11. The repository is watched and re-audited when it changes.