mold_call · ABLESTACK MOLD MCP Server MCP: Risk & Policy

WHAT IT DOES

What mold_call does on ABLESTACK MOLD MCP Server

AI agents invoke mold_call to trigger actions in ABLESTACK MOLD MCP Server. 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 mold_call needs a policy

This tool executes arbitrary API commands against a cloud infrastructure platform. Since it can invoke any API (including delete, destroy, create, financial operations), it must be classified at the highest applicable severity. The open-ended nature means an AI agent could misuse it to destroy VMs, modify networking, incur financial costs, or perform irreversible actions.

From the tool's definition "임의의 MOLD API 명령을 호출합니다" (calls arbitrary MOLD API commands) with "command + params" — executes any CloudStack API command including destructive or financial operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mold_call Rate-limited

mold_call 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": {
    "mold_call": {
      "limits": [
        {
          "counter": "mold_call_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 ABLESTACK MOLD MCP Server, so you can run agents against it safely.

FAQ

Questions about mold_call

What does the mold_call tool do? +

임의의 MOLD API 명령을 호출합니다. (command + params). It is categorised as a Execute tool in the ABLESTACK MOLD MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mold_call? +

Register the ABLESTACK MOLD MCP Server MCP server in PolicyLayer and add a rule for mold_call: 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 ABLESTACK MOLD MCP Server. Nothing to install.

What risk level is mold_call? +

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

Can I rate-limit mold_call? +

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

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

mold_call is provided by the ABLESTACK MOLD MCP Server MCP server (ycyun/ablestack-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.