Desktop (agentify) MCP Server
@agentify/desktop
npm
v0.2.4
Published by @agentify — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
Agentify Desktop control center and MCP server for local AI web sessions
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 − 8 = 92. 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 |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
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 Dynamic evaluation of a non-literal value (chatgpt-controller.mjs)MTC-SRC-010
In the server's implementation (`chatgpt-controller.mjs:60`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ate(url); } async #eval(js) { return await this.page.evaluate(js); } async #emitProgress(patch) { if (
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 chatgpt-controller.mjs
high Dynamic code execution in server code (chatgpt-controller.mjs)MTC-SRC-001
In the server's implementation (`chatgpt-controller.mjs:60`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ate(url); } async #eval(js) { return await this.page.evaluate(js); } async #emitProgress(patch) { if (
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 chatgpt-controller.mjs
high Shell/command execution in server code (bin/agentify-desktop.mjs)MTC-SRC-002
In the server's implementation (`bin/agentify-desktop.mjs:4`): 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 { fileURLToPath, pathToFileURL } from 'node:url'; const __filename = fil
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 bin/agentify-desktop.mjs
high Shell/command execution in server code (chrome-cdp-backend.mjs)MTC-SRC-002
In the server's implementation (`chrome-cdp-backend.mjs:4`): 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'; function sleep(ms) { return new Promise((resolve) => setTimeout(resolve, ms))
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 chrome-cdp-backend.mjs
high Shell/command execution in server code (main.mjs)MTC-SRC-002
In the server's implementation (`main.mjs:7`): 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 { createBrowserBackend, resolveBrowserBackend, resolveChromeDebugP
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 main.mjs
high Shell/command execution in server code (mcp-lib.mjs)MTC-SRC-002
In the server's implementation (`mcp-lib.mjs:1`): 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 path from 'node:path'; import fs from 'node:fs/promises'; import { fileUR
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 mcp-lib.mjs
high Shell/command execution in server code (orchestrator.mjs)MTC-SRC-002
In the server's implementation (`orchestrator.mjs:50`): 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 import('node:child_process'); return await new Promise((resolve) => { const child = spawn(testCommand,
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 orchestrator.mjs
high Shell/command execution in server code (orchestrator/codex.mjs)MTC-SRC-002
In the server's implementation (`orchestrator/codex.mjs:1`): 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 readline from 'node:readline'; import path from 'node:path'; function is
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 orchestrator/codex.mjs
high Shell/command execution in server code (orchestrator/git-diff.mjs)MTC-SRC-002
In the server's implementation (`orchestrator/git-diff.mjs:1`): 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 path from 'node:path'; function run(cmd, args, { cwd, timeoutMs = 60_000
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 orchestrator/git-diff.mjs
What this scan could not see
- No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Versions 1
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 |
|---|---|---|---|---|
v0.2.4 latest |
A 92/100 | 9 | 1.13.0 | 2026-09-07 |
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 @agentify/desktop --onlineOther implementations of Desktop 2
Independent packages implementing the same tool, scanned with the same engine. Compare all 3 side by side →
WebRTC-based MCP server for remote desktop control — screen capture, mouse/keyboard input, shell execution, and more
Windows desktop-control MCP server: screenshot, window mgmt, mouse/keyboard input, and screen-recording. Config-gated tool groups (observe/window/input/record) -- input disabled by default. Local-only, single-machine.
More 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