AI agents call get_holdings_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 investment portfolio data without executing any trades, transferring funds, or modifying account state. While it accesses sensitive financial data (holdings details), the read-only nature and local data retention significantly limit misuse risk. An AI agent using this tool can only view information, not perform financial transactions.
From the tool's definition Tool name is 'get_holdings_tool' and description states it retrieves 'Current investment positions (tickers, quantities, market value, cost basis)' — purely a data retrieval operation with no modification or execution of trades.
Attacks that exploit this kind of access
Current investment positions (tickers, quantities, market value, cost basis). 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_holdings_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_holdings_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_holdings_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_holdings_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_holdings_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 →