run_block · Pl MCP: Risk & Policy

WHAT IT DOES

What run_block does on Pl

AI agents invoke run_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 run_block needs a policy

The tool executes computational blocks within Platforma Desktop, potentially with side effects depending on what those blocks contain. Without knowing block contents, the worst-case scenario is arbitrary execution (similar to Execute category).

From the tool's definition Tool explicitly performs 'run a block' which triggers execution. Sibling tools include 'execute_js' and 'click', indicating this server controls application automation and script execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_block Rate-limited

run_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": {
    "run_block": {
      "limits": [
        {
          "counter": "run_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 run_block

What does the run_block tool do? +

Run a block. Stale upstream blocks are started automatically. 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 run_block? +

Register the Pl MCP server in PolicyLayer and add a rule for run_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 run_block? +

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

Can I rate-limit run_block? +

Yes. Add a rate_limit block to the run_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 run_block completely? +

Set action: deny in the PolicyLayer policy for run_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 run_block? +

run_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.