Check if safe mode is enabled
AI agents call is_safe_mode to retrieve information from AutoBot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about the device's safe mode status. It performs no writes, deletions, code execution, or financial operations. The query returns boolean state information only, making it a Read category tool with low severity—misuse would only expose device configuration details, not cause harm or enable further attacks without combining with Execute or Destructive siblings.
From the tool's definition Tool name 'is_safe_mode' and description 'Check if safe mode is enabled' indicate a query operation that retrieves device status without modifying state.
Attacks that exploit this kind of access
Check if safe mode is enabled. It is categorised as a Read tool in the AutoBot MCP MCP Server, which means it retrieves data without modifying state.
Register the AutoBot MCP server in PolicyLayer and add a rule for is_safe_mode: 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 AutoBot MCP. Nothing to install.
is_safe_mode 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 is_safe_mode 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 is_safe_mode. 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.
is_safe_mode is provided by the AutoBot MCP server (yz0903/autobot-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 →