Stop an app on the device
AI agents invoke adb_stop_app to trigger actions in ADB MCP Server. 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.
This tool executes a command with external side effects—stopping a running application—whose outcome depends on which app is specified as an argument. While not destructive (the app can be restarted), it is an Execute-category tool because it triggers an external operation on a controlled device.
From the tool's definition Tool name 'adb_stop_app' and description 'Stop an app on the device' indicate execution of a command that terminates a running application process on an Android device via ADB (Android Debug Bridge).
Attacks that exploit this kind of access
Stop an app on the device. It is categorised as a Execute tool in the ADB MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for adb_stop_app: 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.
adb_stop_app 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 adb_stop_app 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 adb_stop_app. 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.
adb_stop_app is provided by the ADB MCP Server MCP server (richard0913/adb-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →