AI agents call get_balances_tool to retrieve information from Plaid 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 from linked financial accounts. While the data is financial in nature, the tool itself performs only a read operation—it queries and returns balance data without moving money, changing account state, or executing transactions. The read-only nature of the server and the passive 'lookup' language confirm this is a Read category tool.
From the tool's definition Tool is described as 'Live balance lookup' with optional filtering by account_id. The parent server is explicitly labeled 'read-only' and stated to provide 'financial analysis tools' without side effects.
Attacks that exploit this kind of access
Live balance lookup. Filter by account_id if given. It is categorised as a Read tool in the Plaid MCP Server, which means it retrieves data without modifying state.
Register the Plaid MCP server in PolicyLayer and add a rule for get_balances_tool: 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 Plaid. Nothing to install.
get_balances_tool 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_tool 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_tool. 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_tool is provided by the Plaid MCP server (t-rhex/plaid-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 →