AI agents call accounts 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 sensitive financial data (account types, subtypes, and identifying information) but does not modify, delete, or move money. It is a Read operation. Severity is high because exposure of account identifiers and types could enable account targeting, fraud, or social engineering, even though no direct financial harm occurs from the read itself.
From the tool's definition Tool description explicitly states 'Get all linked bank accounts' — a retrieval operation with no modification or deletion. The server description confirms it 'lets Claude query your bank accounts, balances, and transactions' (query = read-only).
Attacks that exploit this kind of access
Get all linked bank accounts with their type, subtype, and identifying info. 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 accounts: 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.
accounts 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 accounts 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 accounts. 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.
accounts 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 →