AI agents call support_admin_stats to retrieve information from AgentOS without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries support system statistics with no indication of creating, modifying, deleting, or executing operations. It is purely informational in nature. The admin-only restriction is an access control measure that doesn't change the fundamental read-only nature of the operation.
From the tool's definition Tool name and description indicate a statistics retrieval operation ('Get support system statistics'). The 'admin only' access control suggests it returns information about support metrics or activity data rather than performing modifications or side effects.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Get support system statistics (admin only). It is categorised as a Read tool in the AgentOS MCP Server, which means it retrieves data without modifying state.
Register the AgentOS MCP server in PolicyLayer and add a rule for support_admin_stats: 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 AgentOS. Nothing to install.
support_admin_stats 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 support_admin_stats 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 support_admin_stats. 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.
support_admin_stats is provided by the AgentOS MCP server (netflypsb/agentos). 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 →