AI agents call cleanup_runs to permanently remove resources in Openstudio — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The name 'cleanup_runs' in the context of an energy simulation server most likely refers to removing/deleting previous simulation run artifacts (files, results, logs). 'Cleanup' operations are typically irreversible deletions. However, the empty description reduces confidence. Given the blast radius (losing simulation results could be significant), severity is rated high.
From the tool's definition Tool name 'cleanup_runs' — 'cleanup' strongly implies irreversible deletion of simulation run data/files. Description is empty, lowering confidence.
Documented attack patterns abuse exactly the kind of access cleanup_runs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Openstudio, and nothing reaches the server without passing your rules. This is the rule we recommend for cleanup_runs:
{
"version": "1",
"default": "deny",
"hide": [
"cleanup_runs"
]
} cleanup_runs disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
cleanup_runs. It is categorised as a Destructive tool in the Openstudio MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Openstudio MCP server in PolicyLayer and add a rule for cleanup_runs: 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 Openstudio. Nothing to install.
cleanup_runs is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cleanup_runs 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 cleanup_runs. 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.
cleanup_runs is provided by the Openstudio MCP server (natlabrockies/openstudio-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Openstudio, 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.
146 Openstudio tools catalogued and risk-classified — across an index of 43,000+ MCP servers.