AI agents call get_investment_holdings 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 account data without creating, modifying, deleting, or executing anything. However, severity is elevated to 'high' because the data itself is highly sensitive financial information (portfolio composition, valuations, cost basis); misuse by an AI agent could enable unauthorized financial surveillance, investment strategy disclosure, or inform malicious actors about an individual's net…
From the tool's definition Tool name is 'get_investment_holdings' and description states it retrieves 'snapshot of all positions' with ticker, share count, market value, and cost basis—pure data retrieval with no modification or execution.
Attacks that exploit this kind of access
Snapshot of all positions across investment accounts. Each position includes ticker, share count, market value, and (when Plaid has it) 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_investment_holdings: 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_investment_holdings 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_investment_holdings 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_investment_holdings. 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_investment_holdings 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 →