AI agents call get_liabilities 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.
get_liabilities retrieves sensitive financial liability information without modifying, executing, or deleting data. This is fundamentally a Read operation. However, severity is elevated to 'high' rather than 'low' because the data returned—credit card balances, loan terms, mortgage payoff details—is highly sensitive personal financial information.
From the tool's definition Tool description explicitly states it 'Returns' financial data (credit-card APRs, statement balances, student loan terms, mortgage details).
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Returns credit-card APRs and statement balances, student loan terms and balances, and mortgage rate/payoff details for every linked institution that supports Plaid Liabilities. 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: 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 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 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. 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 is provided by the Plaid MCP server (wilderfield/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 →