AI agents call search_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.
This is a Read operation—it retrieves and filters existing financial transaction data without creating, modifying, deleting, or executing any operations. The description explicitly indicates it returns results (rows) from a search query. While it accesses financial data, the tool itself performs no financial transactions, money movement, or irreversible actions.
From the tool's definition Tool name 'search_transactions' and description 'Server-side filtered transaction search. Returns compact rows matching' indicate querying/retrieval of transaction data without modification or deletion.
Attacks that exploit this kind of access
Server-side filtered transaction search. Returns compact rows matching. 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: 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 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 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. 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 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 →