AI agents call monitor-events to retrieve information from ADB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool monitors and displays input events from an Android device in real-time. Monitoring is a read operation that observes system state without modifying data, executing commands, or triggering destructive actions. While it provides visibility into device input, it does not perform side effects or alter the device state.
From the tool's definition Tool name 'monitor-events' with description '实时查看设备输入事件' (real-time view of device input events). The verb '查看' means 'view/monitor', indicating data retrieval without modification or execution of actions.
Documented attack patterns abuse exactly the kind of access monitor-events gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ADB MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for monitor-events:
{
"version": "1",
"default": "deny",
"tools": {
"monitor-events": {}
}
}monitor-events is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
实时查看设备输入事件. It is categorised as a Read tool in the ADB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for monitor-events: 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 MCP Server. Nothing to install.
monitor-events is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the monitor-events 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 monitor-events. 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.
monitor-events is provided by the ADB MCP Server MCP server (jiantao88/android-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ADB MCP Server, 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.
30 ADB MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.