AI agents use create_baseline_osm 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.
Creates or initializes a building energy model file, modifying the project state by adding a new baseline model. This is a write operation (reversible model creation) rather than read-only. Severity is high because a misconfigured baseline model could lead to incorrect energy analysis affecting building design decisions, though it is not destructive (reversible) or financial.
From the tool's definition Tool named 'create_baseline_osm' with context from sibling tools ('add_baseline_system', 'add_air_loop', etc.) and server description indicating 'creation...of models' and 'modification of models'.
Documented attack patterns abuse exactly the kind of access create_baseline_osm 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 create_baseline_osm:
{
"version": "1",
"default": "deny",
"tools": {
"create_baseline_osm": {
"limits": [
{
"counter": "create_baseline_osm_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_baseline_osm 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.
create_baseline_osm. 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 create_baseline_osm: 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.
create_baseline_osm 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 create_baseline_osm 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 create_baseline_osm. 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.
create_baseline_osm 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.