llm_query · FGD Fusion Stack Pro MCP: Risk & Policy

WHAT IT DOES

What llm_query does on FGD Fusion Stack Pro

AI agents invoke llm_query to trigger actions in FGD Fusion Stack Pro. 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 llm_query needs a policy

This tool sends a query to an external LLM service (Grok), which constitutes triggering an external operation. The effects depend on the arguments passed (the query content). It is not a simple local read, as it initiates an outbound API call to a third-party service.

From the tool's definition Tool name 'llm_query' and description 'Ask Grok' — triggers an external operation by sending a query to an external LLM provider (Grok/xAI API).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

llm_query Rate-limited

llm_query 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": {
    "llm_query": {
      "limits": [
        {
          "counter": "llm_query_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 FGD Fusion Stack Pro, so you can run agents against it safely.

FAQ

Questions about llm_query

What does the llm_query tool do? +

Ask Grok. It is categorised as a Execute tool in the FGD Fusion Stack Pro MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on llm_query? +

Register the FGD Fusion Stack Pro MCP server in PolicyLayer and add a rule for llm_query: 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 FGD Fusion Stack Pro. Nothing to install.

What risk level is llm_query? +

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

Can I rate-limit llm_query? +

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

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

llm_query is provided by the FGD Fusion Stack Pro MCP server (mikeychann-hash/mcpm). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.