remove_user_from_group
AI agents call remove_user_from_group to permanently remove resources in AWS IoT SiteWise MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing a user from a group revokes their access permissions, which is typically irreversible without explicit re-addition. This is an IAM/access control modification that could lock out users from resources. The description is empty, lowering confidence, but the name strongly implies a destructive access-control operation. Severity is high due to potential security and access implications.
From the tool's definition Tool name: 'remove_user_from_group' — 'remove' implies deletion of a user-group membership.
Attacks that exploit this kind of access
remove_user_from_group. It is categorised as a Destructive tool in the AWS IoT SiteWise MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the AWS IoT SiteWise MCP Server MCP server in PolicyLayer and add a rule for remove_user_from_group: 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 IoT SiteWise MCP Server. Nothing to install.
remove_user_from_group 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 remove_user_from_group 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 remove_user_from_group. 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.
remove_user_from_group is provided by the AWS IoT SiteWise MCP Server MCP server (awslabs.aws-iot-sitewise-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.