AI agents call get_transactions 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_transactions retrieves transaction records within a specified date range. This is a query/read operation with no side effects on data. However, severity is elevated to 'medium' rather than 'low' because unauthorized access to transaction history exposes sensitive financial information that could enable fraud, identity theft, or financial surveillance.
From the tool's definition Tool description states 'Fetch transactions' — a read operation that retrieves historical financial data without modifying or deleting it. The word 'Fetch' indicates data retrieval only.
Attacks that exploit this kind of access
Fetch transactions in a date range across one or all linked institutions. 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_transactions: 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_transactions 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_transactions 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_transactions. 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_transactions 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 →