AI agents call adb_get_current_activity to retrieve information from LocalAnt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about which Android activity is currently displayed on screen. It performs a read-only query with no side effects—it does not modify the device state, execute code, delete data, or trigger financial transactions. The limited scope (querying current foreground state) and informational nature place it firmly in the Read category.
From the tool's definition Tool name 'adb_get_current_activity' and description 'Get the foreground activity' indicate a query operation that retrieves the current state of the Android foreground without modification or execution of commands.
Attacks that exploit this kind of access
Get the foreground activity. It is categorised as a Read tool in the LocalAnt MCP Server, which means it retrieves data without modifying state.
Register the LocalAnt MCP server in PolicyLayer and add a rule for adb_get_current_activity: 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 LocalAnt. Nothing to install.
adb_get_current_activity 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 adb_get_current_activity 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_get_current_activity. 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_get_current_activity is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →