Set up the usage account for metrics export.
AI agents use setup_usage_account to create or update resources in CopilotMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CopilotMCP environment.
This tool creates or configures a usage account for metrics export. This is a Write-category action because it modifies system state by establishing a new account configuration. It is not Destructive (the action is reversible—the account can be reconfigured or deleted). It is not Financial (no direct money movement), Execute (no arbitrary code execution), or Read (it has side effects).
From the tool's definition Tool name 'setup_usage_account' and description 'Set up the usage account for metrics export' indicate creation or initialization of a new account configuration.
Attacks that exploit this kind of access
Set up the usage account for metrics export. It is categorised as a Write tool in the CopilotMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Copilot MCP server in PolicyLayer and add a rule for setup_usage_account: 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 CopilotMCP. Nothing to install.
setup_usage_account 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_usage_account 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_usage_account. 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_usage_account is provided by the Copilot MCP server (mehrshadshams/copilotmcp). 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 →