render · Kustomize MCP: Risk & Policy

WHAT IT DOES

What render does on Kustomize MCP

AI agents invoke render to trigger actions in Kustomize MCP. 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 render needs a policy

In the context of this Kustomize MCP server, 'render' almost certainly executes a kustomize build/render operation against Kubernetes overlay configurations, which runs external commands and processes configuration files. This is an Execute-category action. Severity is high because rendering arbitrary Kustomize overlays could execute external plugins or generators and expose sensitive configuration data.

From the tool's definition Tool name is 'render'; server description mentions 'rendering overlays' and 'rendering manifest diffs across environments' using Kustomize

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

render Rate-limited

render 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": {
    "render": {
      "limits": [
        {
          "counter": "render_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 Kustomize MCP, so you can run agents against it safely.

FAQ

Questions about render

What does the render tool do? +

render. It is categorised as a Execute tool in the Kustomize MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on render? +

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

What risk level is render? +

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

Can I rate-limit render? +

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

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

render is provided by the Kustomize MCP server (mbrt/kustomize-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.