preview_plm_project · Infrastructure Auto Provisioner MCP

WHAT IT DOES

What preview_plm_project does on Infrastructure Auto Provisioner

AI agents invoke preview_plm_project to trigger actions in Infrastructure Auto Provisioner. 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 preview_plm_project needs a policy

While 'preview' is nominally read-only (it does not apply changes), it executes Pulumi code that could have side effects depending on the project contents and stack state. It runs external operations (Pulumi CLI) whose effects depend on the project/stack arguments provided.

From the tool's definition Tool performs 'preview' operation on Pulumi infrastructure project which executes code to plan changes; sibling tools include 'apply_plm_project_infrastructure' and 'destroy_plm_project_infrastructure' indicating this is part of infrastructure provisioning…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

preview_plm_project Rate-limited

preview_plm_project 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": {
    "preview_plm_project": {
      "limits": [
        {
          "counter": "preview_plm_project_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 Infrastructure Auto Provisioner, so you can run agents against it safely.

FAQ

Questions about preview_plm_project

What does the preview_plm_project tool do? +

Run pulumi preview for a given project and stack. It is categorised as a Execute tool in the Infrastructure Auto Provisioner MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on preview_plm_project? +

Register the Infrastructure Auto Provisioner MCP server in PolicyLayer and add a rule for preview_plm_project: 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 Infrastructure Auto Provisioner. Nothing to install.

What risk level is preview_plm_project? +

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

Can I rate-limit preview_plm_project? +

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

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

preview_plm_project is provided by the Infrastructure Auto Provisioner MCP server (zerosync-co/mcp-server-autoprovisioner). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.