AI agents call get_selected_elements to retrieve information from Revit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about currently selected elements in Revit without creating, modifying, deleting, or executing operations. It has no side effects on the BIM model or external systems. The blast radius is minimal—at worst, it returns information that could inform subsequent operations, but the tool itself poses no direct risk.
From the tool's definition Tool name and description indicate retrieval of data: 'Get elements currently selected in Revit. You can limit the number of returned elements.' The verb 'Get' and the function of retrieving already-selected elements with no modification capability aligns…
Attacks that exploit this kind of access
Get elements currently selected in Revit. You can limit the number of returned elements. It is categorised as a Read tool in the Revit MCP Server, which means it retrieves data without modifying state.
Register the Revit MCP server in PolicyLayer and add a rule for get_selected_elements: 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 Revit. Nothing to install.
get_selected_elements is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_selected_elements 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 get_selected_elements. 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.
get_selected_elements is provided by the Revit MCP server (mohamed-elnahla/revit-mcp-github-copilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →