sampling_callback · Substrate MCP: Risk & Policy

WHAT IT DOES

What sampling_callback does on Substrate

AI agents invoke sampling_callback to trigger actions in Substrate. 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_callback needs a policy

A 'sampling callback' in MCP context typically involves handling model sampling responses and continuing execution pipelines. This falls under Execute as it triggers or resumes external operations. Confidence is moderate because the description is vague and does not detail what side effects the callback invocation may cause.

From the tool's definition 'Handle sampling callback responses' — the tool processes callback responses, implying it triggers or resumes execution flows based on external sampling results

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sampling_callback Rate-limited

sampling_callback 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_callback": {
      "limits": [
        {
          "counter": "sampling_callback_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 Substrate, so you can run agents against it safely.

FAQ

Questions about sampling_callback

What does the sampling_callback tool do? +

Handle sampling callback responses. It is categorised as a Execute tool in the Substrate 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_callback? +

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

What risk level is sampling_callback? +

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

Can I rate-limit sampling_callback? +

Yes. Add a rate_limit block to the sampling_callback 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_callback completely? +

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

sampling_callback is provided by the Substrate MCP server (ivan-saorin/substrate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.