AI agents call adb_dump_ui 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 reads the UI hierarchy structure from an Android device via the uiautomator framework. It has no side effects—it only retrieves information about what is currently displayed. No data is modified, deleted, executed, or created. This is a classic Read operation, with low severity because the output is limited to UI structure metadata that an attacker could also observe visually.
From the tool's definition Tool name 'adb_dump_ui' and description 'Dump the current UI hierarchy (uiautomator)' indicate this retrieves and queries the current state of the Android UI without modifying or executing actions.
Attacks that exploit this kind of access
Dump the current UI hierarchy (uiautomator). 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_dump_ui: 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_dump_ui 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_dump_ui 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_dump_ui. 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_dump_ui 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 →