Medium Risk

put_role_policy

put_role_policy

How to control put_role_policy ↓

What put_role_policy does on Amazon EKS MCP Server

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

Medium Risk

Why put_role_policy needs a policy

The tool creates or modifies IAM role policies, which is a reversible Write operation. Severity is high because misconfigured or overly permissive policies could grant unintended access to AWS resources, creating a significant blast radius for an AI agent. Confidence is 0.85 rather than higher because the description is empty, requiring inference from the tool name and context.

From the tool's definition Tool name 'put_role_policy' indicates creation or modification of IAM role policies. The prefix 'put_' is a standard AWS API verb for creating or updating resources. Context as EKS MCP server suggests IAM policy management.

Documented attack patterns abuse exactly the kind of access put_role_policy gives an agent:

How to control put_role_policy

PolicyLayer is an MCP gateway — it sits between your AI agents and Amazon EKS MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for put_role_policy:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "put_role_policy": {
      "limits": [
        {
          "counter": "put_role_policy_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

put_role_policy 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.

  1. Create a free account and register Amazon EKS MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about put_role_policy

What does the put_role_policy tool do? +

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

How do I enforce a policy on put_role_policy? +

Register the Amazon EKS MCP Server MCP server in PolicyLayer and add a rule for put_role_policy: 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 Amazon EKS MCP Server. Nothing to install.

What risk level is put_role_policy? +

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

Can I rate-limit put_role_policy? +

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

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

put_role_policy is provided by the Amazon EKS MCP Server MCP server (awslabs.eks-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Amazon EKS MCP Server tool call.

Start from Amazon EKS MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

805 Amazon EKS MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.