AI agents call transactions_by_merchant 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 financial transaction data filtered by merchant, which is a read operation with no side effects. However, severity is high because access to bank transaction data is sensitive personal financial information that, if exposed to an untrusted agent, could enable fraud detection, financial profiling, or unauthorized data exfiltration.
From the tool's definition Tool name 'transactions_by_merchant' combined with server description 'query your bank accounts, balances, and transactions through Plaid' indicates data retrieval.
Attacks that exploit this kind of access
transactions_by_merchant. 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 transactions_by_merchant: 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.
transactions_by_merchant 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 transactions_by_merchant 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 transactions_by_merchant. 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.
transactions_by_merchant is provided by the Plaid MCP server (lukew0824/plaid-mcp-server). 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 →