Define locale do device (idioma/país) via setprop e broadcast.
AI agents invoke set_locale to trigger actions in AVD MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes system-level commands (setprop) and triggers Android broadcast intents to change the device locale. This constitutes an Execute action as it runs external operations on the device. Misuse could disrupt running apps or testing workflows by changing the system locale unexpectedly, warranting medium severity.
From the tool's definition 'Define locale do device (idioma/país) via setprop e broadcast' — sets system properties via setprop and triggers a broadcast, which are active system operations on the Android device.
Attacks that exploit this kind of access
Define locale do device (idioma/país) via setprop e broadcast. It is categorised as a Execute tool in the AVD MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AVD MCP Server MCP server in PolicyLayer and add a rule for set_locale: 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 AVD MCP Server. Nothing to install.
set_locale is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the set_locale 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 set_locale. 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.
set_locale is provided by the AVD MCP Server MCP server (jramalho/avd-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 →