AI agents call adb_status to retrieve information from Adb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
adb_status is a query and information-gathering tool. It checks device connectivity status and retrieves device information (model, Android version, SDK level), which are read-only operations. The cleanup of old temp files is a benign maintenance operation. No data creation, modification, code execution, financial transactions, or irreversible deletions occur. The tool falls clearly into the Read category.
From the tool's definition Tool performs device status queries ('Check if the device is connected', 'return device info') and maintenance cleanup ('cleans up old temp files').
Attacks that exploit this kind of access
Check if the device is connected via ADB and return device info (model, Android version, SDK level). Also cleans up old temp files. It is categorised as a Read tool in the Adb MCP Server, which means it retrieves data without modifying state.
Register the Adb MCP server in PolicyLayer and add a rule for adb_status: 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. Nothing to install.
adb_status 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_status 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_status. 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_status is provided by the Adb MCP server (sfaizi24/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 →