stop_block · Pl MCP: Risk & Policy

WHAT IT DOES

What stop_block does on Pl

AI agents invoke stop_block to trigger actions in Pl. 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 stop_block needs a policy

This tool executes a command to stop/terminate a running block, which constitutes execution of an external operation. While not destructive (the block can be restarted), it actively intervenes in system state by terminating processes. The severity is high because unintended block terminations could disrupt workflows, interrupt critical computations, or cause loss of in-progress work.

From the tool's definition The tool name 'stop_block' and description 'Stop a running block' indicate it triggers an action that halts execution of a process. This is an external operation whose effects depend on the block context and state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_block Rate-limited

stop_block 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": {
    "stop_block": {
      "limits": [
        {
          "counter": "stop_block_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 Pl, so you can run agents against it safely.

FAQ

Questions about stop_block

What does the stop_block tool do? +

Stop a running block. It is categorised as a Execute tool in the Pl MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_block? +

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

What risk level is stop_block? +

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

Can I rate-limit stop_block? +

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

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

stop_block is provided by the Pl MCP server (@milaboratories/pl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.