Start an app on the device
AI agents invoke adb_start_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.
Starting an application on a remote device is an Execute operation—it runs code/processes whose side effects are determined by the app being executed. While not immediately destructive, a malicious agent could launch apps that exfiltrate data, modify system settings, or perform unauthorized actions. The severity is high because it enables arbitrary code execution on the managed device with minimal constraints.
From the tool's definition Tool name 'adb_start_app' and description 'Start an app on the device' indicate execution of an application on a remote Android device. This triggers external operations whose effects depend on which app is launched.
Attacks that exploit this kind of access
Start 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_start_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_start_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_start_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_start_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_start_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 →