memory_batch_delete_records
AI agents call memory_batch_delete_records to permanently remove resources in Amazon MQ MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The term 'delete_records' in the tool name strongly indicates permanent removal of data without undo capability. Batch operations amplify the blast radius by affecting multiple records simultaneously. Without a description to clarify constraints or safeguards, this must be classified as Destructive rather than Write.
From the tool's definition Tool name contains 'delete_records' which indicates irreversible deletion of data. The prefix 'batch_' suggests bulk operations affecting multiple records.
Attacks that exploit this kind of access
memory_batch_delete_records. It is categorised as a Destructive tool in the Amazon MQ MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Amazon MQ MCP Server MCP server in PolicyLayer and add a rule for memory_batch_delete_records: 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 MQ MCP Server. Nothing to install.
memory_batch_delete_records 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 memory_batch_delete_records 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 memory_batch_delete_records. 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.
memory_batch_delete_records is provided by the Amazon MQ MCP Server MCP server (awslabs.amazon-mq-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.