AI agents invoke run_simulation to trigger actions in HoudiniMCP. 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.
run_simulation executes a computation-intensive external operation (Houdini physics/particle simulation) whose effects depend on the simulation parameters and scene state. This is an Execute action—it triggers code/operations whose real-world effects (rendered output, scene modifications) are determined by arguments and cannot be predicted without domain expertise.
From the tool's definition Tool named 'run_simulation' on a Houdini 3D modeling/simulation server. Context indicates it triggers Houdini simulations (physics, particle systems, etc.).
Documented attack patterns abuse exactly the kind of access run_simulation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and HoudiniMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for run_simulation:
{
"version": "1",
"default": "deny",
"tools": {
"run_simulation": {
"limits": [
{
"counter": "run_simulation_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_simulation stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
run_simulation. It is categorised as a Execute tool in the HoudiniMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Houdini MCP server in PolicyLayer and add a rule for run_simulation: 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 HoudiniMCP. Nothing to install.
run_simulation 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_simulation 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_simulation. 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_simulation is provided by the Houdini MCP server (katha-begin/houdini-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from HoudiniMCP, 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.
16 HoudiniMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.