AI agents use save_osm_model to create or update resources in Openstudio — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openstudio environment.
The 'save' operation modifies the filesystem by persisting model data (OSM format). This is a Write operation rather than Read (it changes state), and less severe than Destructive (saving is reversible—the previous version may still exist or be recoverable).
From the tool's definition Tool name is 'save_osm_model' which indicates persistent storage of OpenStudio model data. The server context shows this is a building energy simulation system where models are created and modified.
Documented attack patterns abuse exactly the kind of access save_osm_model 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 save_osm_model:
{
"version": "1",
"default": "deny",
"tools": {
"save_osm_model": {
"limits": [
{
"counter": "save_osm_model_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save_osm_model stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
save_osm_model. It is categorised as a Write tool in the Openstudio MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Openstudio MCP server in PolicyLayer and add a rule for save_osm_model: 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.
save_osm_model is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_osm_model 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 save_osm_model. 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.
save_osm_model 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.