AI agents call hooks_model-stats to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports metrics about model routing and statistics. It performs a read-only query operation without side effects, data modification, or destructive actions. The mention of 'Bash hooks' in the truncated description appears contextual rather than indicative of command execution by this specific tool.
From the tool's definition Tool name 'hooks_model-stats' and description indicate it 'Get[s] model routing statistics', a retrieval operation with no modification, deletion, or execution of external commands.
Attacks that exploit this kind of access
Get model routing statistics Use when native Bash hooks (via Claude Code\. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for hooks_model-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 Ruflo. Nothing to install.
hooks_model-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 hooks_model-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 hooks_model-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.
hooks_model-stats is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
hooks_model-stats is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →