say_hello

THE RISK

High Risk

Why say_hello needs a policy

This tool triggers an external operation in Revit (displaying a dialog box), which counts as Execute since it performs an action in an external application. However, it is purely a UI interaction with no data modification or destructive effects, so severity is low. It is primarily a connectivity/health-check tool.

From the tool's definition Display a greeting dialog in Revit. Useful for testing the connection between Claude and Revit.

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

POLICY

How to control say_hello

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "say_hello": {
      "limits": [
        {
          "counter": "say_hello_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

say_hello stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Revit MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Revit MCP tools

Destructive delete_element Delete one or more elements from the Revit model by their element IDs. Destructive operate_element Operate on Revit elements by performing actions such as select, selectionBox, setColor, se Execute send_code_to_revit Send C code to Revit for execution. The code will be inserted into a template with access Write color_elements Color elements in the current view based on a category and parameter value. Each unique pa Write store_project_data Store or update Revit project metadata in the local database. This captures project inform Write store_room_data Store or update room metadata for a specific Revit project in the local database. Rooms ar Write create_grid Create a grid system in Revit with smart spacing generation. Supports both X-axis (vertica Write create_level Create one or more levels in Revit at specified elevations. Levels define horizontal plane

All 25 Revit MCP tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Revit MCP → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about say_hello

What does the say_hello tool do? +

Display a greeting dialog in Revit. Useful for testing the connection between Claude and Revit. It is categorised as a Execute tool in the Revit MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on say_hello? +

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

What risk level is say_hello? +

say_hello is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit say_hello? +

Yes. Add a rate_limit block to the say_hello 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 say_hello completely? +

Set action: deny in the PolicyLayer policy for say_hello. 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 say_hello? +

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

Enforce policy on every Revit MCP tool call.

Start from Revit MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →