AI agents call nodus_admin_stats to retrieve information from Nodusai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves read-only administrative statistics about query counts and platform breakdowns. It has no side effects, does not modify data, and presents no financial risk. The [ADMIN] designation indicates privileged access but the underlying operation is purely informational. Severity is low because misuse would only expose non-sensitive aggregate metrics rather than user data or enabling harmful actions.
From the tool's definition [ADMIN] Platform stats: total queries, breakdown by platform — retrieves aggregated statistics about platform usage with no modification capability.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
[ADMIN] Platform stats: total queries, breakdown by platform. It is categorised as a Read tool in the Nodusai MCP Server, which means it retrieves data without modifying state.
Register the Nodusai MCP server in PolicyLayer and add a rule for nodus_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 Nodusai. Nothing to install.
nodus_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 nodus_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 nodus_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.
nodus_admin_stats is provided by the Nodusai MCP server (nodusai-your-prediction-broker/nodusai-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 →