AI agents invoke run_sweep to trigger actions in Spicelib. 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 external circuit simulations (spicelib backend) whose outcomes depend on user-supplied parameters and circuit specifications. While not destructive or financial, it triggers computational operations that consume resources and produce results based on arbitrary inputs. Misuse could involve resource exhaustion through large parameter ranges, or generating misleading simulation results.
From the tool's definition The tool name 'run_sweep' combined with server description context 'parameter sweep analyses' and sibling tools 'run_ac_analysis', 'run_dc_op', 'run_transient' indicate this executes circuit simulations.
Documented attack patterns abuse exactly the kind of access run_sweep gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Spicelib, and nothing reaches the server without passing your rules. This is the rule we recommend for run_sweep:
{
"version": "1",
"default": "deny",
"tools": {
"run_sweep": {
"limits": [
{
"counter": "run_sweep_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_sweep 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_sweep. It is categorised as a Execute tool in the Spicelib MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Spicelib MCP server in PolicyLayer and add a rule for run_sweep: 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 Spicelib. Nothing to install.
run_sweep 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_sweep 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_sweep. 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_sweep is provided by the Spicelib MCP server (lucasgerads/spicelib-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Spicelib, 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.
4 Spicelib tools catalogued and risk-classified — across an index of 43,000+ MCP servers.