Medium Risk

place_family

Place a family instance at a specified location in the Revit model

How to control place_family ↓

What place_family does on MCP server for Revit - Python

AI agents use place_family to create or update resources in MCP server for Revit - Python — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP server for Revit - Python environment.

Medium Risk

Why place_family needs a policy

This tool creates new content (places a family instance) in the Revit model, which is a write/create operation. It modifies the model by adding geometry/elements, but this is reversible via undo in Revit. The severity is high because misuse could corrupt or significantly alter a BIM model used for architectural/engineering design and construction.

From the tool's definition Place a family instance at a specified location in the Revit model

Documented attack patterns abuse exactly the kind of access place_family gives an agent:

How to control place_family

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP server for Revit - Python, and nothing reaches the server without passing your rules. This is the rule we recommend for place_family:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "place_family": {
      "limits": [
        {
          "counter": "place_family_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

place_family 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.

  1. Create a free account and register MCP server for Revit - Python — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about place_family

What does the place_family tool do? +

Place a family instance at a specified location in the Revit model. It is categorised as a Write tool in the MCP server for Revit - Python MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on place_family? +

Register the MCP server for Revit - Python MCP server in PolicyLayer and add a rule for place_family: 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 MCP server for Revit - Python. Nothing to install.

What risk level is place_family? +

place_family is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit place_family? +

Yes. Add a rate_limit block to the place_family 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.

How do I block place_family completely? +

Set action: deny in the PolicyLayer policy for place_family. 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.

What MCP server provides place_family? +

place_family is provided by the MCP server for Revit - Python MCP server (mcp-servers-for-revit/mcp-server-for-revit-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP server for Revit - Python tool call.

Start from MCP server for Revit - Python, 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.

20 MCP server for Revit - Python tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.