Create a QBO Customer. DisplayName is required. Other common fields: CompanyName, PrimaryEmailAddr.Address, BillAddr, Notes. Returns the full Customer object. Audit tag is applied to Notes (anti-spoof: caller-supplied [kaizen:...] fragments are stripped).
AI agents use qbo_create_customer to create or update resources in Kaizen Qbo — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kaizen Qbo environment.
This tool creates new data in QBO that persists and affects financial records. Customer creation is reversible (can be deleted/marked inactive), placing it in Write rather than Destructive. However, severity is high because creating fraudulent or incorrect customers in a financial system could lead to invoice/payment misrouting, accounting errors, or facilitate invoice fraud.
From the tool's definition Tool creates a new Customer record in QuickBooks Online (qbo_create_customer) with required DisplayName and optional fields like CompanyName, PrimaryEmailAddr, BillAddr, Notes. Returns the full Customer object, confirming persistent creation.
Attacks that exploit this kind of access
Create a QBO Customer. DisplayName is required. Other common fields: CompanyName, PrimaryEmailAddr.Address, BillAddr, Notes. Returns the full Customer object. Audit tag is applied to Notes (anti-spoof: caller-supplied [kaizen:...] fragments are stripped). It is categorised as a Write tool in the Kaizen Qbo MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kaizen Qbo MCP server in PolicyLayer and add a rule for qbo_create_customer: 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 Kaizen Qbo. Nothing to install.
qbo_create_customer 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 qbo_create_customer 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 qbo_create_customer. 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.
qbo_create_customer is provided by the Kaizen Qbo MCP server (kaizen-qbo-mcp-server). 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 →