AI agents use onboard_customer to create or update resources in SpherePay — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SpherePay environment.
The tool name 'onboard_customer' strongly implies creating a new customer record in the SpherePay system, which is a Write operation. On a financial platform, onboarding a customer may involve creating accounts, setting up wallets, or initiating KYC processes — all reversible writes. However, the description is empty, which reduces confidence.
From the tool's definition Tool name 'onboard_customer' on a financial platform (SpherePay) that manages customers, bank accounts, wallets, and transfers.
Attacks that exploit this kind of access
onboard_customer. It is categorised as a Write tool in the SpherePay MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SpherePay MCP server in PolicyLayer and add a rule for onboard_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 SpherePay. Nothing to install.
onboard_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 onboard_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 onboard_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.
onboard_customer is provided by the SpherePay MCP server (danchev/spherepay-mcp). 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 →