instance_action · Oci MCP: Risk & Policy

WHAT IT DOES

What instance_action does on Oci

AI agents invoke instance_action to trigger actions in Oci. 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 instance_action needs a policy

This tool triggers operational actions on cloud compute instances — starting, stopping, or resetting them. These are external operations with real-world side effects (e.g., stopping a running instance causes downtime). While some actions are reversible (START/STOP), the blast radius is high since misuse could cause service outages.

From the tool's definition Perform a safe instance action (START, STOP, RESET, SOFTRESET, SOFTSTOP)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

instance_action Rate-limited

instance_action 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": {
    "instance_action": {
      "limits": [
        {
          "counter": "instance_action_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 Oci, so you can run agents against it safely.

FAQ

Questions about instance_action

What does the instance_action tool do? +

Perform a safe instance action (START, STOP, RESET, SOFTRESET, SOFTSTOP). It is categorised as a Execute tool in the Oci MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on instance_action? +

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

What risk level is instance_action? +

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

Can I rate-limit instance_action? +

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

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

instance_action is provided by the Oci MCP server (oreo-tech/oci-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.