llm_predict · MCP LLM Integration Server MCP: Risk & Policy

WHAT IT DOES

What llm_predict does on MCP LLM Integration Server

AI agents invoke llm_predict to trigger actions in MCP LLM Integration 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 llm_predict needs a policy

This tool executes inference on a local LLM using a customizable inference function. While it may appear to only read/generate text, it actively runs computation on a local model with potentially arbitrary text input, which could trigger side effects depending on the inference function implementation.

From the tool's definition 'Process text input through a local LLM' — runs input through a local language model inference function

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

llm_predict Rate-limited

llm_predict 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_predict": {
      "limits": [
        {
          "counter": "llm_predict_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 MCP LLM Integration Server, so you can run agents against it safely.

FAQ

Questions about llm_predict

What does the llm_predict tool do? +

Process text input through a local LLM. It is categorised as a Execute tool in the MCP LLM Integration 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 llm_predict? +

Register the MCP LLM Integration Server MCP server in PolicyLayer and add a rule for llm_predict: 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 MCP LLM Integration Server. Nothing to install.

What risk level is llm_predict? +

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

Can I rate-limit llm_predict? +

Yes. Add a rate_limit block to the llm_predict 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_predict completely? +

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

llm_predict is provided by the MCP LLM Integration Server MCP server (raptor7197/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.