4 tools. 3 can modify or destroy data without limits.
1 destructive tool with no built-in limits. Policy required.
Last updated:
Destructive tools (manage_hyperpod_cluster_nodes) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (manage_hyperpod_stacks, update_hp_cluster) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
manage_hyperpod_cluster_nodes:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
manage_hyperpod_stacks:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
describe_hp_cluster:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Amazon SageMaker AI MCP Server server exposes 1 destructive tools including manage_hyperpod_cluster_nodes. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Amazon SageMaker AI MCP Server server has 2 write tools including manage_hyperpod_stacks, update_hp_cluster. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
4 tools across 3 categories: Destructive, Read, Write. 1 are read-only. 3 can modify, create, or delete data.
One line change. Instead of running the Amazon SageMaker AI MCP Server server directly, prefix it with Intercept: intercept -c amazon-sagemaker-ai-mcp-server.yaml -- npx -y @awslabs.sagemaker-ai-mcp-server. Download a pre-built policy from policylayer.com/policies/amazon-sagemaker-ai-mcp-server and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.