Developerz Ai Ui Debugger MCP Server
@developerz.ai/ui-debugger-mcp
npm
v1.9.0
Source verified
Published by developerz-ai — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Autonomous UI debugging MCP server. Give a goal; a fast agent drives the browser/desktop, finds bugs + visual issues, and reports back.
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 9
high Shell/command execution in server code (dist/adapters/android/adb.js)MTC-SRC-002
In the server's implementation (`dist/adapters/android/adb.js:24`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from 'node:child_process'; import { promisify } from 'node:util'; import { AdbError } from '../../errors.js
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/adapters/android/adb.js
high Shell/command execution in server code (dist/adapters/android/android-adapter.js)MTC-SRC-002
In the server's implementation (`dist/adapters/android/android-adapter.js:21`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { AdapterError, UiDebuggerError } from '../../errors.js'; import { capWai
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/adapters/android/android-adapter.js
high Shell/command execution in server code (dist/adapters/desktop/atspi.js)MTC-SRC-002
In the server's implementation (`dist/adapters/desktop/atspi.js:278`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: init.exec ?? ((args) => exec('busctl', args)); } async readTree(opts = {}) { const maxNodes = opts.maxNo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/adapters/desktop/atspi.js
high Shell/command execution in server code (dist/adapters/desktop/capture.js)MTC-SRC-002
In the server's implementation (`dist/adapters/desktop/capture.js:62`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: await this.#exec(tool, captureArgs(tool, file)); const buffer = await readFile(file);
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/adapters/desktop/capture.js
high Shell/command execution in server code (dist/adapters/desktop/desktop-adapter.js)MTC-SRC-002
In the server's implementation (`dist/adapters/desktop/desktop-adapter.js:18`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { AdapterError, UiDebuggerError } from '../../errors.js'; import { capWai
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/adapters/desktop/desktop-adapter.js
high Shell/command execution in server code (dist/adapters/desktop/input.js)MTC-SRC-002
In the server's implementation (`dist/adapters/desktop/input.js:191`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const out = await this.#exec(XDOTOOL, args).catch((error) => { // An expired per-call cap (`proc.ts`) ar
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/adapters/desktop/input.js
high Shell/command execution in server code (dist/adapters/desktop/proc.js)MTC-SRC-002
In the server's implementation (`dist/adapters/desktop/proc.js:16`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from 'node:child_process'; import { promisify } from 'node:util'; import { ExecTimeoutError } from '../../e
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/adapters/desktop/proc.js
high Shell/command execution in server code (dist/services/replay.js)MTC-SRC-002
In the server's implementation (`dist/services/replay.js:24`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: rt { spawn } from 'node:child_process'; import { existsSync } from 'node:fs'; import { stat } from 'node:fs/promises'; i
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/services/replay.js
medium Dynamic module load from a non-literal (dist/services/debug-service.js)MTC-SRC-005
In the server's implementation (`dist/services/debug-service.js:299`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const session = this.#require(session_id); if (session.status !== 'running') { throw new SessionSe
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/services/debug-service.js
Tools 5
Each tool and what it can reach — statically extracted from the published source.
send_messagenetwork egressdescribeno sensitive capabilityend_sessionno sensitive capabilityget_findingsno sensitive capabilitystart_debugno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (5 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 8
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v1.9.0 latest |
A 94/100 | 9 | 1.13.0 | 2026-09-07 |
v1.8.0 |
A 94/100 | 9 | 1.13.0 | 2026-09-05 |
v1.7.0 |
A 94/100 | 9 | 1.12.1 | 2026-07-29 |
v1.6.0 |
A 94/100 | 9 | 1.12.1 | 2026-07-27 |
v1.5.2 |
A 94/100 | 9 | 1.12.1 | 2026-07-27 |
Show 3 more versions ↓
v1.4.0 |
A 94/100 | 9 | 1.10.0 | 2026-07-27 |
v1.3.1 |
A 94/100 | 9 | 1.10.0 | 2026-07-25 |
v1.2.0 |
A 94/100 | 9 | 1.9.0 | 2026-07-24 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @developerz.ai/ui-debugger-mcp --onlineMore in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand