AI agents call get_identity_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 queries and retrieves identity information without creating, modifying, deleting, or executing operations. While the data is sensitive (PII), the risk is limited to unauthorized information disclosure rather than irreversible action or financial transaction. Severity is low because exposure is confined to read access with no ability to modify accounts or move funds.
From the tool's definition Tool retrieves 'account holder names, emails, phones, addresses' from financial institutions with no modification capability. Server is explicitly described as 'read-only MCP server' and the tool name includes 'get_' prefix indicating data retrieval.
Attacks that exploit this kind of access
Account holder names, emails, phones, addresses as reported by the 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 get_identity_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.
get_identity_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 get_identity_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 get_identity_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.
get_identity_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 →