tf_plan · RedisNexus MCP: Risk & Policy

WHAT IT DOES

What tf_plan does on RedisNexus

AI agents invoke tf_plan to trigger actions in RedisNexus. 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 tf_plan needs a policy

Terraform plan executes the Terraform binary against real infrastructure providers to compute a diff. While it does not apply changes, it does make API calls to cloud providers, may read secrets, and its output reveals sensitive infrastructure topology. The 'run' verb confirms active execution rather than a passive read.

From the tool's definition "Run terraform plan to preview infrastructure changes"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tf_plan Rate-limited

tf_plan 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": {
    "tf_plan": {
      "limits": [
        {
          "counter": "tf_plan_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 RedisNexus, so you can run agents against it safely.

FAQ

Questions about tf_plan

What does the tf_plan tool do? +

Run terraform plan to preview infrastructure changes. It is categorised as a Execute tool in the RedisNexus MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tf_plan? +

Register the RedisNexus MCP server in PolicyLayer and add a rule for tf_plan: 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 RedisNexus. Nothing to install.

What risk level is tf_plan? +

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

Can I rate-limit tf_plan? +

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

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

tf_plan is provided by the RedisNexus MCP server (rajkumar-madhu/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.