Manage EKS CloudFormation stacks with both read and write operations. This tool provides operations for managing EKS CloudFormation stacks, including creating templates, deploying stacks, retrieving stack information, and deleting stacks. It serves as the primary mechanism for creating and manag...
Single-target operation
Part of the Amazon EKS MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use manage_eks_stacks to create or modify resources in Amazon EKS MCP Server. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call manage_eks_stacks repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Amazon EKS MCP Server.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
manage_eks_stacks:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Amazon EKS MCP Server policy for all 16 tools.
Agents calling write-class tools like manage_eks_stacks have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Manage EKS CloudFormation stacks with both read and write operations. This tool provides operations for managing EKS CloudFormation stacks, including creating templates, deploying stacks, retrieving stack information, and deleting stacks. It serves as the primary mechanism for creating and managing EKS clusters through CloudFormation, enabling standardized cluster creation, configuration updates, and resource cleanup. IMPORTANT: Use this tool instead of 'aws eks create-cluster', 'aws eks delete-cluster', 'eksctl create cluster', 'eksctl delete cluster', or similar CLI commands. IMPORTANT: Use this tool's standardized templates for creating EKS clusters with proper VPC configuration, networking, security groups, and EKS auto mode. DO NOT create EKS clusters by generating CloudFormation templates from scratch. ## Requirements - The server must be run with the `--allow-write` flag for generate, deploy, and delete operations - For deploy and delete operations, the stack must have been created by this tool - For template_file parameter, the path must be absolute and accessible to the server ## Operations - **generate**: Create a CloudFormation template at the specified absolute path with the cluster name embedded - **deploy**: Deploy a CloudFormation template from the specified absolute path (creates a new stack or updates an existing one) - **describe**: Get detailed information about a CloudFormation stack for a specific cluster - **delete**: Delete a CloudFormation stack for the specified cluster ## Response Information The response type varies based on the operation: - generate: Returns CallToolResult with the template path - deploy: Returns CallToolResult with stack name, ARN, and cluster name - describe: Returns CallToolResult with stack details, outputs, and status - delete: Returns CallToolResult with stack name, ID, and cluster name ## Usage Tips - Use the describe operation first to check if a cluster already exists - For safety, this tool will only modify or delete stacks that it created - Stack creation typically takes 15-20 minutes to complete - Use absolute paths for template files (e.g., '/home/user/templates/eks-template.yaml') - The cluster name is used to derive the CloudFormation stack name Args: ctx: MCP context operation: Operation to perform (generate, deploy, describe, or delete) template_file: Absolute path for the CloudFormation template (for generate and deploy operations) cluster_name: Name of the EKS cluster (for all operations) Returns: ManageEksStacksResponse: Response with fields populated based on the operation performed. 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.
Add a rule in your Intercept YAML policy under the tools section for manage_eks_stacks. 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.
manage_eks_stacks is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the manage_eks_stacks 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.
Set action: deny in the Intercept policy for manage_eks_stacks. 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.
manage_eks_stacks 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.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.