AI agents call list_linked_institutions 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 queries and retrieves sensitive financial metadata (list of connected banks/brokerages) without side effects. Severity is high because the data returned (which institutions a user has connected) is sensitive financial information that could be misused for social engineering, targeted attacks, or privacy violations, despite being read-only.
From the tool's definition Tool name 'list_linked_institutions' and description 'Returns every bank/brokerage currently linked' indicate retrieval of linked financial institution data without modification.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Returns every bank/brokerage currently linked, including a. 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 list_linked_institutions: 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.
list_linked_institutions 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 list_linked_institutions 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 list_linked_institutions. 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.
list_linked_institutions 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 →