tofu · Cloud Pilot MCP: Risk & Policy

WHAT IT DOES

What tofu does on Cloud Pilot MCP

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

WHY IT NEEDS A POLICY

Why tofu needs a policy

An AI agent can call tofu faster than any human can review — one bad instruction and it creates or modifies resources in Cloud Pilot MCP by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tofu Rate-limited

tofu 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": {
    "tofu": {
      "limits": [
        {
          "counter": "tofu_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 Cloud Pilot MCP, so you can run agents against it safely.

FAQ

Questions about tofu

What does the tofu tool do? +

Manage infrastructure as code with OpenTofu (Terraform-compatible). It is categorised as a Write tool in the Cloud Pilot MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on tofu? +

Register the Cloud Pilot MCP server in PolicyLayer and add a rule for tofu: 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 Cloud Pilot MCP. Nothing to install.

What risk level is tofu? +

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

Can I rate-limit tofu? +

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

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

tofu is provided by the Cloud Pilot MCP server (vitalemazo/cloud-pilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.