select_block · Pl MCP: Risk & Policy

WHAT IT DOES

What select_block does on Pl

AI agents invoke select_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 select_block needs a policy

This tool performs a UI interaction (navigation) in a desktop application, which constitutes executing an external operation (UI automation). It doesn't merely read data; it actively changes the UI state. Severity is medium because misuse could disrupt UI workflows, though it doesn't delete data or move money.

From the tool's definition 'Navigate the desktop UI to show a specific block' — triggers a UI navigation/interaction action in the desktop application

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

select_block Rate-limited

select_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": {
    "select_block": {
      "limits": [
        {
          "counter": "select_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 select_block

What does the select_block tool do? +

Navigate the desktop UI to show a specific 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 select_block? +

Register the Pl MCP server in PolicyLayer and add a rule for select_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 select_block? +

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

Can I rate-limit select_block? +

Yes. Add a rate_limit block to the select_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 select_block completely? +

Set action: deny in the PolicyLayer policy for select_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 select_block? +

select_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.