Get and save logs from logcat on a specific Android device
AI agents call get_device_logs to retrieve information from Android Device without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves diagnostic logs from an Android device's logcat system without executing code, modifying data, or triggering side effects. However, the severity is elevated to medium because logcat may contain sensitive information (authentication tokens, personal data, API keys, user activity) that could be exposed if an agent misuses this capability to exfiltrate logs.
From the tool's definition Tool name and description explicitly state 'Get and save logs from logcat' — a read-only retrieval operation with no modification or execution of device state.
Attacks that exploit this kind of access
Get and save logs from logcat on a specific Android device. It is categorised as a Read tool in the Android Device MCP Server, which means it retrieves data without modifying state.
Register the Android Device MCP server in PolicyLayer and add a rule for get_device_logs: 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 Android Device. Nothing to install.
get_device_logs 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 get_device_logs 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 get_device_logs. 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.
get_device_logs is provided by the Android Device MCP server (prashant1507/android-device-mcp). 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 →