AI agents invoke run_transient 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 a transient analysis simulation on a circuit, which is a computational operation with side effects (consuming resources, generating output data). It does not create persistent data artifacts (Write), delete anything (Destructive), move money (Financial), or merely retrieve data (Read).
From the tool's definition Tool name 'run_transient' belongs to a family of simulation analysis tools (run_ac_analysis, run_dc_op, run_sweep) that execute circuit simulations.
Documented attack patterns abuse exactly the kind of access run_transient 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_transient:
{
"version": "1",
"default": "deny",
"tools": {
"run_transient": {
"limits": [
{
"counter": "run_transient_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_transient 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_transient. 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_transient: 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_transient 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_transient 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_transient. 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_transient 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.