run_mps_sim
AI agents invoke run_mps_sim to trigger actions in M/M/1 and M/M/c Queue Simulation Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes simulations (likely queuing or scheduling simulations) whose behavior depends on input arguments (parameters, configuration). Simulation execution is an Execute-category action. Severity is medium because simulation tools typically have limited external blast radius—they compute and return results without modifying persistent data or triggering irreversible actions.
From the tool's definition Tool name 'run_mps_sim' combined with sibling tools like 'run_simulation', 'run_mmc_simulation', and 'run_multiple_simulations' all performing simulation execution.
Attacks that exploit this kind of access
run_mps_sim. It is categorised as a Execute tool in the M/M/1 and M/M/c Queue Simulation Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the M/M/1 and M/M/c Queue Simulation Server MCP server in PolicyLayer and add a rule for run_mps_sim: 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.
run_mps_sim is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_mps_sim 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 run_mps_sim. 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.
run_mps_sim 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 →