Launch an app by package name. Optionally specify an activity.
AI agents invoke adb_app_launch 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.
Launching apps is an Execute action: it runs external code/operations on the target device whose consequences depend on the arguments (which app is launched). While not destructive on its own, the blast radius is high because a malicious agent could launch apps that access sensitive data, make payments, delete files, or trigger unwanted behaviors.
From the tool's definition Tool description states it 'Launch[es] an app by package name', which triggers external operations on an Android device whose effects depend on which app is launched. The tool enables arbitrary app execution via ADB (Android Debug Bridge).
Attacks that exploit this kind of access
Launch an app by package name. Optionally specify an activity. 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_app_launch: 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_app_launch 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_app_launch 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_app_launch. 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_app_launch is provided by the ADB MCP Server MCP server (lll-404/adb-mcp-server). 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 →