sensor_set
AI agents use sensor_set to create or update resources in Android Emulator — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Android Emulator environment.
Based on the server description mentioning control over virtual sensors (accelerometer, gyroscope) and the sibling tools 'sensor_get' and 'sensor_status', 'sensor_set' almost certainly sets/modifies sensor values on the Android emulator. This is a Write operation as it modifies emulator state reversibly.
From the tool's definition Tool name 'sensor_set' on a server that 'provides control over virtual sensors like the accelerometer and gyroscope'
Attacks that exploit this kind of access
sensor_set. It is categorised as a Write tool in the Android Emulator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Android Emulator MCP server in PolicyLayer and add a rule for sensor_set: 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 Emulator. Nothing to install.
sensor_set is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the sensor_set 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 sensor_set. 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.
sensor_set is provided by the Android Emulator MCP server (janjetze/android-emulator-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 →