AI agents use create_window to create or update resources in IFC Bonsai MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your IFC Bonsai MCP environment.
Creating a window in an IFC model is a reversible Write operation—it adds new data to the model that can be modified or deleted. It does not execute arbitrary code, destroy data irreversibly, or move money. The medium severity reflects that miscreating windows could corrupt the architectural model, but the effects are recoverable.
From the tool's definition Tool name 'create_window' and sibling tools (create_door, create_mesh_ifc, create_slab, create_roof) all perform IFC model creation/modification operations.
Documented attack patterns abuse exactly the kind of access create_window gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and IFC Bonsai MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for create_window:
{
"version": "1",
"default": "deny",
"tools": {
"create_window": {
"limits": [
{
"counter": "create_window_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_window 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_window. It is categorised as a Write tool in the IFC Bonsai MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the IFC Bonsai MCP server in PolicyLayer and add a rule for create_window: 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 IFC Bonsai MCP. Nothing to install.
create_window 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_window 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_window. 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_window is provided by the IFC Bonsai MCP server (show2instruct/ifc-bonsai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 52 IFC Bonsai MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
52 IFC Bonsai MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.