Sampling · MCP Server MCP: Risk & Policy

WHAT IT DOES

What Sampling does on MCP Server

AI agents invoke Sampling to trigger actions in 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 Sampling needs a policy

This tool submits prompts to an external LLM (Azure OpenAI) and retrieves completions. It is not a simple read — it actively triggers external API calls and computation whose outputs depend entirely on the inputs. This qualifies as Execute, since it runs external operations. Misuse could lead to prompt injection, unauthorized API usage, cost escalation, or generation of harmful content.

From the tool's definition LLM completion requests (streaming and non-streaming) — triggers external LLM inference operations via Azure OpenAI integration

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

Sampling Rate-limited

Sampling 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": {
    "Sampling": {
      "limits": [
        {
          "counter": "sampling_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 Server, so you can run agents against it safely.

FAQ

Questions about Sampling

What does the Sampling tool do? +

LLM completion requests (streaming and non-streaming). It is categorised as a Execute tool in the 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 Sampling? +

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

What risk level is Sampling? +

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

Can I rate-limit Sampling? +

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

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

Sampling is provided by the MCP Server MCP server (krishanu-das-05/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.