AI agents call get_balances to retrieve information from Poke Bank without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves account balance information without modifying or deleting data, making it a Read operation. Severity is high rather than low because: (1) it accesses sensitive financial data; (2) unauthorized access could reveal account balances and enable fraud planning; (3) the broader context involves banking APIs and authenticated sessions, indicating real financial accounts.
From the tool's definition Tool name 'get_balances' and description 'Get current balances for a specific bank account' indicate data retrieval with no modification or deletion. However, the context of banking data access elevates severity.
Attacks that exploit this kind of access
Get current balances for a specific bank account. It is categorised as a Read tool in the Poke Bank MCP Server, which means it retrieves data without modifying state.
Register the Poke Bank MCP server in PolicyLayer and add a rule for get_balances: 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 Poke Bank. Nothing to install.
get_balances 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 get_balances 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 get_balances. 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.
get_balances is provided by the Poke Bank MCP server (kacperkwapisz/poke-bank). 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 →