AI agents call balances 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 financial data (account balances and credit limits) without modifying or deleting anything, making it a Read operation. Severity is high because unauthorized access to account balances could enable fraud, identity theft, or financial planning attacks, even though the tool itself performs no destructive actions.
From the tool's definition The tool description explicitly states it 'Get[s] current and available balances for all accounts' and returns account balance information. This is a read-only retrieval operation with no modification capability.
Attacks that exploit this kind of access
Get current and available balances for all accounts. For credit cards, also returns the credit limit. 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 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 Plaid. Nothing to install.
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 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 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.
balances is provided by the Plaid MCP server (lukew0824/plaid-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 →