AI agents call adb_current_package 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 performs a read-only operation that queries the current state of an Android device via ADB (Android Debug Bridge). It retrieves the name of the foreground package, which is informational metadata with no side effects, data modifications, or system changes. The blast radius is minimal—knowing which app is currently in the foreground poses no inherent risk of data loss or system compromise.
From the tool's definition Tool name 'adb_current_package' and description 'Get the current foreground package name' indicate a query operation that retrieves information about the currently active Android package without modifying any state.
Attacks that exploit this kind of access
Get the current foreground package name. 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_current_package: 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_current_package 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_current_package 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_current_package. 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_current_package 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 →