manos-mcp
npm
v0.2.0
Published by ryanperkins — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
A CLI MCP server for ad-hoc UI testing of Android & iOS apps — a tight act+observe loop, device-condition control, log/crash & network capture, OCR targeting, accessibility audits, and session recording that exports a replayable flow.
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 − 6.3 = 94. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −6.3 | Untrusted input concatenated into a command sink MTC-SRC-009 | injection |
2. Client adoption risk — 94 − 7 = 87. 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 |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
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.
In the server's implementation (`assets/frida/sidecar.py:23`): 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: n", help="package id to spawn (catches startup traffic)") ap.add_argument("--hook", required=True, help="path to okh
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 assets/frida/sidecar.py
In the server's implementation (`dist/core/maestro.js:45`): 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 res = await exec("maestro", args, { timeoutMs: opts.timeoutMs ?? 300_000, allowNonZe
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/core/maestro.js
In the server's implementation (`dist/core/maestroDriver.js:51`): 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 res = await exec("maestro", ["--udid", deviceId, "hierarchy"], { timeoutMs: 60_000 }); // maestro prints
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/core/maestroDriver.js
In the server's implementation (`dist/core/maestroSession.js: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: { execSync } from "node:child_process"; import { Client } from "@modelcontextprotocol/sdk/client/index.js"; import { Std
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/core/maestroSession.js
In the server's implementation (`dist/core/netcapture.js: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: ync, spawn } from "node:child_process"; import { mkdtempSync, writeFileSync } from "node:fs"; import { readFile, writeFi
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/core/netcapture.js
In the server's implementation (`dist/core/ocr.js:31`): 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: ive: true }); await exec("swiftc", [VISION_SRC, "-O", "-o", VISION_BIN], { timeoutMs: 120_000 }); if (!existsSyn
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/core/ocr.js
In the server's implementation (`dist/drivers/android.js:87`): 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: : args; return exec(this.adbPath, full, { timeoutMs: opts?.timeoutMs ?? 20_000 }); } shell(serial, comm
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/drivers/android.js
In the server's implementation (`dist/drivers/ios.js:77`): 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: opts) { return exec("xcrun", ["simctl", ...args], { timeoutMs: opts?.timeoutMs ?? 30_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 dist/drivers/ios.js
In the server's implementation (`dist/util/exec.js: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"; export class ExecError extends Error { result; constructor(message, resu
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/util/exec.js
In the server's implementation (`dist/util/toolchain.js:38`): 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 r = await exec(file, versionArgs, { timeoutMs: 5_000, allowNonZero: true }); version = (r.stdout |
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/util/toolchain.js
In the server's implementation (`dist/core/maestroSession.js:168`): A shell/process command assembled from concatenated or interpolated values is command injection when any part is attacker-influenced — the OWASP canonical RCE flow. Verify what reaches the interpolated value. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: y { const out = execSync(`pgrep -f '${WARM_JVM_SIGNATURE}'`, { stdio: ["ignore", "pipe", "ignore"],
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/core/maestroSession.js
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 |
|---|---|---|---|---|
v0.2.0 latest |
B 87/100 | 11 | 1.13.0 | 2026-09-07 |
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.
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 manos-mcp --online
The Stripe Agent Toolkit enables popular agent frameworks including LangChain and Vercel's AI SDK to integrate with Stripe APIs through function calling.
MCP (Model Context Protocol) server for AgentGate. Enables Claude and other MCP-compatible AI assistants to request approvals.
Scan any website for AI agent readiness, payment protocols, and discovery endpoints
MCP server for aigently security guardrails — reads static catalog-data JSON, zero API dependency
Governed threat modeling, code threat verification, traceability & compliance, as MCP tools.
Governed threat modeling, code threat verification, traceability & compliance, as MCP tools.