Ats MCP Server
ats-mcp
npm
v0.4.0
Published by actiontestscript — 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.
MCP server that lets LLMs drive ActionTestScript (ATS) — test automation across web, mobile, desktop, and API, powered by ats-core's REPL.
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 − 11.7 = 88. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −11.7 | Untrusted input concatenated into a command sink ×4 MTC-SRC-009 | injection |
2. Client adoption risk — 88 − 7 = 81. 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.
Findings 6
high Shell/command execution in server code (dist/ats-client.js)MTC-SRC-002
In the server's implementation (`dist/ats-client.js:8`): 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: aseUrl; } async exec(command, timeoutSeconds = 30) { const resp = await fetch(`${this.baseUrl}/cmd`, {
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/ats-client.js
high Shell/command execution in server code (dist/ats-launcher.js)MTC-SRC-002
In the server's implementation (`dist/ats-launcher.js:10`): 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 { createServer } from "node:net"; import * as fs from "node:fs"; import *
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/ats-launcher.js
medium Untrusted input concatenated into a command sink (dist/tools/actions.js)MTC-SRC-009
In the server's implementation (`dist/tools/actions.js:7`): 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: const res = await ats.exec(`click -> ${args.element}`, 30); return formatResult(res); } export const hoverSchema =
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/tools/actions.js
medium Untrusted input concatenated into a command sink (dist/tools/capture.js)MTC-SRC-009
In the server's implementation (`dist/tools/capture.js:24`): 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: const res = await ats.exec(`find -> ${args.selector}`, 30); return formatResult(res); } // ── Browser introspectio
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/tools/capture.js
medium Untrusted input concatenated into a command sink (dist/tools/channels.js)MTC-SRC-009
In the server's implementation (`dist/tools/channels.js:10`): 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: const res = await ats.exec(`channel-start -> ${args.name} -> ${args.target}`, 120); return formatResult(res); } ex
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/tools/channels.js
medium Untrusted input concatenated into a command sink (dist/tools/window.js)MTC-SRC-009
In the server's implementation (`dist/tools/window.js:11`): 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: const res = await ats.exec(`scripting -> ${code}`, 30); return formatResult(res); } export const windowResizeSchem
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/tools/window.js
Tools 30
Each tool and what it can reach — statically extracted from the published source.
capture_treereads sensitive dataclickno sensitive capabilityconsole_logsno sensitive capabilitydragno sensitive capabilitydropno sensitive capabilityevaluate_jsno sensitive capabilityfile_uploadno sensitive capabilityfind_elementsno sensitive capabilitygoto_urlno sensitive capabilityhandle_dialogno sensitive capability
Show 20 more tools ↓
hoverno sensitive capabilitynavigate_backno sensitive capabilitynavigate_forwardno sensitive capabilitynetwork_cookiesno sensitive capabilitynetwork_detailno sensitive capabilitynetwork_listno sensitive capabilitypress_keyno sensitive capabilityrefreshno sensitive capabilityrun_ats_blockno sensitive capabilityscreenshotno sensitive capabilityscrollno sensitive capabilityselect_optionno sensitive capabilitysend_keysno sensitive capabilitystart_channelno sensitive capabilitystop_channelno sensitive capabilityswitch_channelno sensitive capabilitywindow_closeno sensitive capabilitywindow_new_tabno sensitive capabilitywindow_resizeno sensitive capabilitywindow_switchno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (30 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 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 |
|---|---|---|---|---|
v0.4.0 latest |
B 81/100 | 6 | 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 ats-mcp --onlineMore in Security & Testing
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.