create_deployment · Kubernetes MCP: Risk & Policy

WHAT IT DOES

What create_deployment does on Kubernetes

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

WHY IT NEEDS A POLICY

Why create_deployment needs a policy

This tool creates new Kubernetes deployment resources, which modifies cluster state by provisioning compute resources, networking, and scheduling workloads. While reversible (deployments can be deleted), the creation of workloads has significant blast radius if misused by an agent—it could deploy malicious containers, consume cluster resources, or create security vulnerabilities.

From the tool's definition Tool is named 'create_deployment' and described as 'Create a new Kubernetes deployment'. The verb 'Create' and the action of deploying new workloads to a Kubernetes cluster indicates data/resource creation with side effects on the cluster state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_deployment Rate-limited

create_deployment 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": {
    "create_deployment": {
      "limits": [
        {
          "counter": "create_deployment_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 Kubernetes, so you can run agents against it safely.

FAQ

Questions about create_deployment

What does the create_deployment tool do? +

Create a new Kubernetes deployment. It is categorised as a Write tool in the Kubernetes MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_deployment? +

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

What risk level is create_deployment? +

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

Can I rate-limit create_deployment? +

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

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

create_deployment is provided by the Kubernetes MCP server (mcp-server-kubernetes). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.