Run LTspice in batch mode for the currently loaded netlist.
AI agents invoke runSimulation to trigger actions in Ltspice. 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 LTspice, an external circuit simulator, which performs computations and generates output files/state changes based on the provided netlist. While not shell-arbitrary, it triggers a complex external process whose side effects (temporary files, CPU usage, output generation) depend on netlist arguments.
From the tool's definition Tool description states 'Run LTspice in batch mode for the currently loaded netlist.' The verb 'Run' combined with 'in batch mode' indicates execution of an external simulation engine (LTspice) with effects determined by the netlist content and simulator…
Documented attack patterns abuse exactly the kind of access runSimulation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ltspice, and nothing reaches the server without passing your rules. This is the rule we recommend for runSimulation:
{
"version": "1",
"default": "deny",
"tools": {
"runSimulation": {
"limits": [
{
"counter": "runsimulation_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}runSimulation 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 LTspice in batch mode for the currently loaded netlist. It is categorised as a Execute tool in the Ltspice MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ltspice MCP server in PolicyLayer and add a rule for runSimulation: 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 Ltspice. Nothing to install.
runSimulation 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 runSimulation 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 runSimulation. 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.
runSimulation is provided by the Ltspice MCP server (xuio/ltspice-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ltspice, 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.
71 Ltspice tools catalogued and risk-classified — across an index of 43,000+ MCP servers.