Low Risk

list_api_versions

List all available API versions in the Kubernetes cluster. This tool discovers all available API versions on the Kubernetes cluster, which is helpful for determining the correct apiVersion to use when managing Kubernetes resources. It returns both core APIs and API groups, useful for verifying A...

Part of the Amazon EKS MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call list_api_versions to retrieve information from Amazon EKS MCP Server without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though list_api_versions only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

amazon-eks-mcp-server.yaml
tools:
  list_api_versions:
    rules:
      - action: allow

See the full Amazon EKS MCP Server policy for all 16 tools.

Tool Name list_api_versions
Category Read
Risk Level Low

View all 16 tools →

Agents calling read-class tools like list_api_versions have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the list_api_versions tool do? +

List all available API versions in the Kubernetes cluster. This tool discovers all available API versions on the Kubernetes cluster, which is helpful for determining the correct apiVersion to use when managing Kubernetes resources. It returns both core APIs and API groups, useful for verifying API compatibility and discovering available resources. ## Response Information The response includes core APIs (like 'v1'), API groups with versions (like 'apps/v1'), extension APIs (like 'networking.k8s.io/v1'), and any Custom Resource Definition (CRD) APIs installed in the cluster. ## Usage Tips - Use this tool before creating or updating resources to ensure API compatibility - Different Kubernetes versions may have different available APIs - Some APIs may be deprecated or removed in newer Kubernetes versions - Custom resources will only appear if their CRDs are installed in the cluster Args: ctx: MCP context cluster_name: Name of the EKS cluster Returns: ApiVersionsResponse with list of available API versions. It is categorised as a Read tool in the Amazon EKS MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_api_versions? +

Add a rule in your Intercept YAML policy under the tools section for list_api_versions. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Amazon EKS MCP Server MCP server.

What risk level is list_api_versions? +

list_api_versions is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list_api_versions? +

Yes. Add a rate_limit block to the list_api_versions rule in your Intercept 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 list_api_versions completely? +

Set action: deny in the Intercept policy for list_api_versions. 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 list_api_versions? +

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

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.