This record as markdown: /tools/aws/json-arrtrim.md
What json_arrtrim does on AWS
AI agents call json_arrtrim to permanently remove resources in AWS, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why json_arrtrim is rated Critical
Trimming an array removes elements outside the given range. This is an irreversible in-place modification that destroys data (the removed array elements), making it Destructive rather than merely Write. If the range is misconfigured, data loss is permanent.
From the tool's definition Trim array at path to include only elements within range — elements outside the specified range are permanently removed from the array.
Attacks that exploit this kind of access
The rule that runs json_arrtrim safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AWS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For json_arrtrim, this is the rule to start with:
json_arrtrim is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect AWS, apply this rule, and every json_arrtrim call is checked against it from then on.
Questions about json_arrtrim
Trim array at path to include only elements within range. Args: key: The name of the key path: The path in the JSON document start: Start index (inclusive) stop: Stop index (inclusive) Returns: New array length or error message. It is categorised as a Destructive tool in the AWS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AWS MCP server in PolicyLayer and add a rule for json_arrtrim: 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 AWS. Nothing to install.
json_arrtrim 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_arrtrim 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_arrtrim. 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_arrtrim is provided by the AWS MCP server (@awslabs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on AWS, and thousands of servers like it.
Across the catalogue