Sets up cross-account access for CloudWatch monitoring.
AI agents use setup_cross_account_access to create or update resources in AWS_CloudGuardMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AWS_CloudGuardMCP environment.
The tool modifies AWS account permissions and access configurations, which affects authentication and authorization boundaries. This is categorized as Write rather than Execute because it configures infrastructure state rather than triggering transient operations.
From the tool's definition Tool performs 'setup' of 'cross-account access' which modifies AWS IAM/access control configuration. This is a reversible configuration change that creates or modifies access policies and roles.
Attacks that exploit this kind of access
Sets up cross-account access for CloudWatch monitoring. It is categorised as a Write tool in the AWS_CloudGuardMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AWS_CloudGuard MCP server in PolicyLayer and add a rule for setup_cross_account_access: 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_CloudGuardMCP. Nothing to install.
setup_cross_account_access 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 setup_cross_account_access 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 setup_cross_account_access. 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.
setup_cross_account_access is provided by the AWS_CloudGuard MCP server (madhurprash/aws_cloudguardmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →