Calculate theoretical M/M/1 performance metrics
AI agents call calculate_metrics to retrieve information from M/M/1 and M/M/c Queue Simulation Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs theoretical calculations on queueing system parameters and returns computed metrics (e.g., average queue length, waiting time). It retrieves no external data, modifies no state, executes no code or simulations, and cannot cause destructive or financial effects. It is a pure computational read operation.
From the tool's definition Tool name 'calculate_metrics' and description 'Calculate theoretical M/M/1 performance metrics' indicate data retrieval and mathematical computation with no side effects, no state modification, and no external operations.
Attacks that exploit this kind of access
Calculate theoretical M/M/1 performance metrics. It is categorised as a Read tool in the M/M/1 and M/M/c Queue Simulation Server MCP Server, which means it retrieves data without modifying state.
Register the M/M/1 and M/M/c Queue Simulation Server MCP server in PolicyLayer and add a rule for calculate_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 M/M/1 and M/M/c Queue Simulation Server. Nothing to install.
calculate_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 calculate_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 calculate_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.
calculate_metrics is provided by the M/M/1 and M/M/c Queue Simulation Server MCP server (kiyoung8/simulation_by_simpy_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 →