Aggregate tool invocation counts, total duration, and error counts. If sessionId is given, stats are scoped to that session; otherwise scoped to the N most recently active sessions across all agents (default 50).
AI agents call get_tool_usage_stats to retrieve information from AgentWatch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a statistics and metrics query tool that aggregates historical data about tool usage. It reads and summarizes existing telemetry information without modifying, deleting, or executing anything. The scope parameter (sessionId or default to N recent sessions) is a filter, not an action. This fits the Read category: retrieves data with no side effects.
From the tool's definition Tool description states it retrieves 'aggregate tool invocation counts, total duration, and error counts' — purely retrieval/query operations with no modification, deletion, or execution capabilities. No side effects mentioned.
Documented attack patterns abuse exactly the kind of access get_tool_usage_stats gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AgentWatch, and nothing reaches the server without passing your rules. This is the rule we recommend for get_tool_usage_stats:
{
"version": "1",
"default": "deny",
"tools": {
"get_tool_usage_stats": {}
}
}get_tool_usage_stats is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Aggregate tool invocation counts, total duration, and error counts. If sessionId is given, stats are scoped to that session; otherwise scoped to the N most recently active sessions across all agents (default 50). It is categorised as a Read tool in the AgentWatch MCP Server, which means it retrieves data without modifying state.
Register the AgentWatch MCP server in PolicyLayer and add a rule for get_tool_usage_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 AgentWatch. Nothing to install.
get_tool_usage_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 get_tool_usage_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 get_tool_usage_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.
get_tool_usage_stats is provided by the AgentWatch MCP server (mishanefedov/agentwatch). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AgentWatch, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 AgentWatch tools catalogued and risk-classified — across an index of 43,000+ MCP servers.