AI agents call hook_stats to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns statistical information about hooks. It performs no side effects, creates no new data, executes no code, and does not delete or modify anything. The use of 'Get' in the description is a strong signal of Read category behavior. The blast radius of misuse is minimal since the agent cannot cause harm by reading statistics.
From the tool's definition Tool name 'hook_stats' and description 'Get statistics about registered hooks: total, by type, blocking vs non-blocking' indicate a read-only retrieval operation that queries existing hook metadata without modifying, executing, or deleting any data.
Attacks that exploit this kind of access
Get statistics about registered hooks: total, by type, blocking vs non-blocking. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.
Register the Mementos MCP server in PolicyLayer and add a rule for hook_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 Mementos. Nothing to install.
hook_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 hook_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 hook_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.
hook_stats is provided by the Mementos MCP server (@hasna/mementos). 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 →