Generate security-approved IAM policy for MSK Kafka ESM with scoped permissions. Uses pre-approved templates, not LLM generation.
AI agents call secure_esm_msk_policy to retrieve information from Amazon SageMaker AI MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a policy template and formats it for output. It does not create, modify, delete, or execute operations on AWS resources. Even though the output (an IAM policy) could be used to affect permissions, the tool itself only reads from and returns pre-defined templates. The policy must be separately applied by another action (Write category).
From the tool's definition Tool generates and returns an IAM policy document based on pre-approved templates. The verb 'Generate' combined with 'Uses pre-approved templates, not LLM generation' indicates this is a lookup/retrieval operation that produces output without modifying AWS…
Attacks that exploit this kind of access
Generate security-approved IAM policy for MSK Kafka ESM with scoped permissions. Uses pre-approved templates, not LLM generation. It is categorised as a Read tool in the Amazon SageMaker AI MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amazon SageMaker AI MCP Server MCP server in PolicyLayer and add a rule for secure_esm_msk_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 SageMaker AI MCP Server. Nothing to install.
secure_esm_msk_policy is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the secure_esm_msk_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.
Set action: deny in the PolicyLayer policy for secure_esm_msk_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.
secure_esm_msk_policy is provided by the Amazon SageMaker AI MCP Server MCP server (awslabs.sagemaker-ai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.