execute_add · Shadcn Registry manager MCP: Risk & Policy

WHAT IT DOES

What execute_add does on Shadcn Registry manager

AI agents invoke execute_add to trigger actions in Shadcn Registry manager. 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 execute_add needs a policy

The tool executes a workflow that modifies the user's project by adding components. 'Execute' and 'actually adds' indicate active side effects beyond a simple write — it runs a multi-step automated workflow.

From the tool's definition "Execute the full add component workflow - this actually adds the component to the user"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_add Rate-limited

execute_add 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": {
    "execute_add": {
      "limits": [
        {
          "counter": "execute_add_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 Shadcn Registry manager, so you can run agents against it safely.

FAQ

Questions about execute_add

What does the execute_add tool do? +

Execute the full add component workflow - this actually adds the component to the user. It is categorised as a Execute tool in the Shadcn Registry manager MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_add? +

Register the Shadcn Registry manager MCP server in PolicyLayer and add a rule for execute_add: 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 Shadcn Registry manager. Nothing to install.

What risk level is execute_add? +

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

Can I rate-limit execute_add? +

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

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

execute_add is provided by the Shadcn Registry manager MCP server (reuvenaor/shadcn-registry-manager). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.