Add a value to the cache only if the key doesn't exist.
AI agents use cache_add to create or update resources in Amazon SageMaker AI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Amazon SageMaker AI MCP Server environment.
This tool creates or modifies cache state reversibly. It does not delete, execute code, move money, or trigger external operations. The blast radius of cache pollution is limited to potentially stale or incorrect cached values, but the operation itself can be undone by clearing or updating the cache.
From the tool's definition Tool description states it 'Add[s] a value to the cache' - a create/modify operation on cached data. The conditional 'only if the key doesn't exist' indicates it creates new cache entries rather than destructively replacing existing ones.
Attacks that exploit this kind of access
Add a value to the cache only if the key doesn't exist. It is categorised as a Write tool in the Amazon SageMaker AI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Amazon SageMaker AI MCP Server MCP server in PolicyLayer and add a rule for cache_add: 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.
cache_add 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 cache_add 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 cache_add. 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.
cache_add 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.