launch_instance · OCI MCP Server MCP: Risk & Policy

WHAT IT DOES

What launch_instance does on OCI MCP Server

AI agents invoke launch_instance to trigger actions in OCI MCP Server. 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 launch_instance needs a policy

Launching a compute instance is an Execute-category action because it initiates a running system whose behavior is determined by its configuration and can perform any operation a server is capable of. While not immediately destructive, it triggers resource provisioning and potential ongoing charges, making misuse high-severity.

From the tool's definition Tool description: 'Launch a compute instance.' The verb 'launch' combined with 'compute instance' indicates starting a resource whose behavior and effects depend entirely on the instance configuration and workloads it runs.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

launch_instance Rate-limited

launch_instance 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": {
    "launch_instance": {
      "limits": [
        {
          "counter": "launch_instance_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about launch_instance

What does the launch_instance tool do? +

Launch a compute instance. Use shape_ocpus/memory for flex shapes. It is categorised as a Execute tool in the OCI MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on launch_instance? +

Register the OCI MCP Server MCP server in PolicyLayer and add a rule for launch_instance: 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 MCP Server. Nothing to install.

What risk level is launch_instance? +

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

Can I rate-limit launch_instance? +

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

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

launch_instance is provided by the OCI MCP Server MCP server (sarthak-pansare/oci-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.