Clear container at path (array or object).
AI agents call json_clear to permanently remove resources in Amazon SageMaker AI MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool performs an irreversible operation that removes data from a JSON container (array or object). While the scope may be limited to a specific path, the operation cannot be undone without external backups or recovery mechanisms. This qualifies as Destructive rather than Write because it wipes data rather than modifying it reversibly.
From the tool's definition Tool name 'json_clear' with description 'Clear container at path (array or object)' indicates irreversible deletion or erasure of data structures. The verb 'clear' in this context means to remove all contents from a container.
Attacks that exploit this kind of access
Clear container at path (array or object). It is categorised as a Destructive tool in the Amazon SageMaker AI MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Amazon SageMaker AI MCP Server MCP server in PolicyLayer and add a rule for json_clear: 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.
json_clear is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the json_clear 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 json_clear. 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.
json_clear 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.