AI agents call get_liabilities_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 sensitive financial liability information without performing any write, destructive, or financial transaction operations. While Read category applies, severity is rated 'high' rather than 'low' because unauthorized access to liabilities data (APRs, balances, due dates) could enable identity theft, financial fraud, or social engineering attacks that depend on detailed personal financial exposure.
From the tool's definition Tool description explicitly states retrieval of financial data: 'Credit cards, student loans, mortgages with APRs, balances, due dates.' The server description emphasizes 'read-only MCP server' and 'analyze their real bank, credit card, loan, and brokerage…
Attacks that exploit this kind of access
Credit cards, student loans, mortgages with APRs, balances, due dates. 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_liabilities_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_liabilities_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_liabilities_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_liabilities_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_liabilities_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 →