Retrieve the text of the last toast message displayed on the device. Useful for verifying notifications, error messages, and user feedback.
AI agents call get_toast to retrieve information from MCP Android Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries toast notification text from the device—a form of data retrieval with no side effects, no code execution, no data modification, and no destructive capability. It falls cleanly into the Read category. Severity is low because toast messages are ephemeral UI feedback with no security-sensitive data exposure risk in typical scenarios.
From the tool's definition Tool name 'get_toast' and description 'Retrieve the text of the last toast message displayed on the device' indicate a read-only operation that queries existing UI state without modifying or executing actions.
Documented attack patterns abuse exactly the kind of access get_toast gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Android Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for get_toast:
{
"version": "1",
"default": "deny",
"tools": {
"get_toast": {}
}
}get_toast is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Retrieve the text of the last toast message displayed on the device. Useful for verifying notifications, error messages, and user feedback. It is categorised as a Read tool in the MCP Android Agent MCP Server, which means it retrieves data without modifying state.
Register the MCP Android Agent MCP server in PolicyLayer and add a rule for get_toast: 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 MCP Android Agent. Nothing to install.
get_toast 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_toast 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_toast. 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_toast is provided by the MCP Android Agent MCP server (nim444/mcp-android-server-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 28 MCP Android Agent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
28 MCP Android Agent tools catalogued and risk-classified — across an index of 42,500+ MCP servers.