AI agents invoke run_ui_test to trigger actions in Adb. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
UI testing tools execute arbitrary test code whose behavior depends on the test arguments/payload. This is Execute rather than Read because it actively runs operations on the device (not merely inspecting state), and the effects are triggered by the AI agent's choice of test logic. Severity is high because misuse could cause unintended app state changes, device instability, or data exposure during test execution.
From the tool's definition Tool name 'run_ui_test' combined with server description stating 'advanced tools like UI testing' indicates execution of automated testing code.
Documented attack patterns abuse exactly the kind of access run_ui_test gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Adb, and nothing reaches the server without passing your rules. This is the rule we recommend for run_ui_test:
{
"version": "1",
"default": "deny",
"tools": {
"run_ui_test": {
"limits": [
{
"counter": "run_ui_test_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_ui_test stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
run_ui_test. It is categorised as a Execute tool in the Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Adb MCP server in PolicyLayer and add a rule for run_ui_test: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Adb. Nothing to install.
run_ui_test is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_ui_test rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for run_ui_test. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
run_ui_test is provided by the Adb MCP server (wolfcoming/adb_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Adb, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
48 Adb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.