process_command · CAD- MCP: Risk & Policy

WHAT IT DOES

What process_command does on CAD-MCP

AI agents invoke process_command to trigger actions in CAD-MCP. 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 process_command needs a policy

This tool processes arbitrary structured commands with open-ended {action, params} arguments. The broad scope means it could invoke any capability on the CAD system — drawing, layer management, file operations, or even destructive actions. The generic nature of 'process structured command' with arbitrary params makes it an execution gateway.

From the tool's definition '处理结构化命令' (process structured commands) with parameters {action, params} — generic command processor that executes arbitrary structured commands

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

process_command Rate-limited

process_command 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": {
    "process_command": {
      "limits": [
        {
          "counter": "process_command_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 CAD-MCP, so you can run agents against it safely.

FAQ

Questions about process_command

What does the process_command tool do? +

处理结构化命令。参数: {action, params}. It is categorised as a Execute tool in the CAD-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 process_command? +

Register the CAD- MCP server in PolicyLayer and add a rule for process_command: 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 CAD-MCP. Nothing to install.

What risk level is process_command? +

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

Can I rate-limit process_command? +

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

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

process_command is provided by the CAD- MCP server (piexl/cad-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.