AI agents invoke run_osw to trigger actions in Openstudio. 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 an external workflow system (OpenStudio) that runs building energy simulations. The effects are dependent on arguments (workflow definition, model parameters, simulation settings) and represent code/process execution rather than simple data retrieval or modification.
From the tool's definition Tool name 'run_osw' and description 'Start an OpenStudio workflow (OSW) run asynchronously' indicates execution of external workflows/simulations.
Documented attack patterns abuse exactly the kind of access run_osw 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 run_osw:
{
"version": "1",
"default": "deny",
"tools": {
"run_osw": {
"limits": [
{
"counter": "run_osw_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_osw 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.
Start an OpenStudio workflow (OSW) run asynchronously. It is categorised as a Execute tool in the Openstudio MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Openstudio MCP server in PolicyLayer and add a rule for run_osw: 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.
run_osw 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_osw 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_osw. 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_osw 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.