// MCP TOOL REFERENCE

AMAZON SAGEMAKER AI MCP SERVER TOOLS

4 tools from the Amazon SageMaker AI MCP Server MCP Server, categorised by risk level.

View the Amazon SageMaker AI MCP Server policy →

READ TOOLS

describe_hp_cluster Describe a SageMaker HyperPod cluster. Args: ctx: MCP context cluster_name: REQUIRED - Target cluster for describe cluster api region_...

WRITE TOOLS

manage_hyperpod_stacks Manage SageMaker HyperPod Cluster through CloudFormation stacks. This tool provides operations for managing HyperPod CloudFormation stacks, includ... update_hp_cluster Update a SageMaker HyperPod clusters. Notes: - before using this tool, ensure you first have the most recent cluster instance group configurat...

DESTRUCTIVE TOOLS

manage_hyperpod_cluster_nodes Manage SageMaker HyperPod clusters and nodes with both read and write operations. This tool provides operations for managing SageMaker HyperPod cl...

// FAQ

How many tools does the Amazon SageMaker AI MCP Server MCP server have? +

The Amazon SageMaker AI MCP Server MCP server exposes 4 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Amazon SageMaker AI MCP Server tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Amazon SageMaker AI MCP Server server.

What risk categories do Amazon SageMaker AI MCP Server tools fall into? +

Amazon SageMaker AI MCP Server tools are categorised as Read (1), Write (2), Destructive (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

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

GET STARTED →