sample_llm · MCP Everything MCP: Risk & Policy

WHAT IT DOES

What sample_llm does on MCP Everything

AI agents use sample_llm to create or update resources in MCP Everything — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Everything environment.

WHY IT NEEDS A POLICY

Why sample_llm needs a policy

An AI agent can call sample_llm faster than any human can review — one bad instruction and it creates or modifies resources in MCP Everything by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sample_llm Rate-limited

sample_llm stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sample_llm": {
      "limits": [
        {
          "counter": "sample_llm_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 Everything, so you can run agents against it safely.

FAQ

Questions about sample_llm

What does the sample_llm tool do? +

sample_llm. It is categorised as a Write tool in the MCP Everything MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sample_llm? +

Register the MCP Everything MCP server in PolicyLayer and add a rule for sample_llm: 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 Everything. Nothing to install.

What risk level is sample_llm? +

sample_llm is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit sample_llm? +

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

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

sample_llm is provided by the MCP Everything MCP server (s2005/mcp-everything). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.