Open recent apps / app switcher
AI agents invoke press_recent_apps to trigger actions in Enhanced 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 an Android device action (pressing the recent apps button) through ADB. It doesn't read data, write/modify persistent data, or delete anything — it triggers an external UI operation on the device. Severity is low as it merely opens the app switcher with minimal blast radius.
From the tool's definition 'Open recent apps / app switcher' — triggers a device UI action (opening the recents screen) on an Android device via ADB
Attacks that exploit this kind of access
Open recent apps / app switcher. It is categorised as a Execute tool in the Enhanced ADB MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Enhanced ADB MCP Server MCP server in PolicyLayer and add a rule for press_recent_apps: 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 Enhanced ADB MCP Server. Nothing to install.
press_recent_apps 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 press_recent_apps 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 press_recent_apps. 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.
press_recent_apps is provided by the Enhanced ADB MCP Server MCP server (rahulkr/r_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 →