AI agents call system.guard_metrics to retrieve information from Dynamic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metrics (counters) related to guard concurrency and rate-limiting. It is a read-only operation that queries system state for observability purposes, with no side effects. While it provides information about system capacity and limits, this is informational only and poses minimal risk if exposed to an AI agent.
From the tool's definition Tool name 'system.guard_metrics' and description 'Get guard concurrency/rate-limit counters' indicate a query operation that retrieves monitoring/observability data without modifying state or triggering external actions.
Attacks that exploit this kind of access
Get guard concurrency/rate-limit counters. It is categorised as a Read tool in the Dynamic MCP Server, which means it retrieves data without modifying state.
Register the Dynamic MCP server in PolicyLayer and add a rule for system.guard_metrics: 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 Dynamic. Nothing to install.
system.guard_metrics 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 system.guard_metrics 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 system.guard_metrics. 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.
system.guard_metrics is provided by the Dynamic MCP server (mcpland/dynamic-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 →