AI agents call search_transactions_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 and queries transaction data without side effects. It performs a search operation (a read-only retrieval) across existing transaction records. While the underlying data is sensitive financial information, the tool itself is categorized as Read because it does not create, modify, delete, or execute any operations.
From the tool's definition Tool is described as 'Fuzzy search across transaction description and merchant name' and exists on a 'read-only MCP server' for financial data analysis. No modification, deletion, or execution of operations is performed.
Attacks that exploit this kind of access
Fuzzy search across transaction description and merchant name. 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 search_transactions_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.
search_transactions_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 search_transactions_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 search_transactions_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.
search_transactions_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 →