AI agents call list_bank_accounts to retrieve information from SpherePay without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and lists existing bank account data with optional filtering. It performs no modifications, deletions, or financial transactions. While it accesses sensitive financial data (bank accounts), the read-only nature and lack of destructive capability classify it as Read category with low severity—an AI agent listing accounts poses minimal risk compared to tools that execute transfers or delete data.
From the tool's definition Tool name 'list_bank_accounts' and description 'List SpherePay bank accounts with pagination. Optionally filter by customer_id' indicate a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List SpherePay bank accounts with pagination. Optionally filter by customer_id. It is categorised as a Read tool in the SpherePay MCP Server, which means it retrieves data without modifying state.
Register the SpherePay MCP server in PolicyLayer and add a rule for list_bank_accounts: 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.
list_bank_accounts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_bank_accounts 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 list_bank_accounts. 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.
list_bank_accounts 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 →