AI agents call list_accounts_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 account information without creating, modifying, deleting, or executing any actions. The read-only nature of the server and the passive nature of listing accounts confirm this is a Read operation. Severity is low because account enumeration alone carries minimal risk if misused by an agent—it would only expose account structure, not enable financial transactions or data destruction.
From the tool's definition Tool name 'list_accounts_tool' and description 'List every account across every linked institution' indicate a retrieval operation with no modification.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
List every account across every linked institution. 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_accounts_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.
list_accounts_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 list_accounts_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 list_accounts_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.
list_accounts_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 →