bulc_run_fds · BULC Building Designer MCP: Risk & Policy

WHAT IT DOES

What bulc_run_fds does on BULC Building Designer

AI agents invoke bulc_run_fds to trigger actions in BULC Building Designer. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why bulc_run_fds needs a policy

This tool executes an external simulation engine (FDS) rather than merely reading or writing data. While not destructive (simulation results don't overwrite the model by default) or financial, it runs a complex external operation whose resource consumption and side effects (CPU usage, file generation, thermal analysis outputs) depend on the current model configuration.

From the tool's definition Tool name 'bulc_run_fds' and description 'Start FDS simulation' indicate execution of an external fire simulation software (FDS - Fire Dynamics Simulator).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bulc_run_fds Rate-limited

bulc_run_fds 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches BULC Building Designer, so you can run agents against it safely.

FAQ

Questions about bulc_run_fds

What does the bulc_run_fds tool do? +

Start FDS simulation. It is categorised as a Execute tool in the BULC Building Designer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on bulc_run_fds? +

Register the BULC Building Designer MCP server in PolicyLayer and add a rule for bulc_run_fds: 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 BULC Building Designer. Nothing to install.

What risk level is bulc_run_fds? +

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

Can I rate-limit bulc_run_fds? +

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

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

bulc_run_fds is provided by the BULC Building Designer MCP server (using76/bulc_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.