add_block · Pl MCP: Risk & Policy

WHAT IT DOES

What add_block does on Pl

AI agents use add_block to create or update resources in Pl — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pl environment.

WHY IT NEEDS A POLICY

Why add_block needs a policy

This tool creates new blocks within a project, which modifies the project state reversibly. It does not execute arbitrary code (that would be Execute), delete data (Destructive), or move money (Financial). Adding a block is a write operation that changes project configuration.

From the tool's definition Tool description states 'Add a block to an opened project', indicating creation/modification of project structure. The spec parameter allows selection of either published or local dev blocks.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_block Rate-limited

add_block stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_block": {
      "limits": [
        {
          "counter": "add_block_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 add_block

What does the add_block tool do? +

Add a block to an opened project. Spec can be from-registry-v2 (for published blocks) or dev-v2 (for local dev blocks). It is categorised as a Write tool in the Pl MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_block? +

Register the Pl MCP server in PolicyLayer and add a rule for add_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 add_block? +

add_block is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_block? +

Yes. Add a rate_limit block to the add_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 add_block completely? +

Set action: deny in the PolicyLayer policy for add_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 add_block? +

add_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.