AI agents call get_portfolio to retrieve information from Ib Async without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing portfolio information and market values without modifying, deleting, or executing any operations. It has no side effects and presents minimal risk. Even if an AI agent calls it repeatedly or for unintended accounts, the worst case is information disclosure of financial holdings, which is less severe than write, execute, or destructive actions.
From the tool's definition Tool name 'get_portfolio' and description 'Get portfolio positions with market values' indicate a read-only retrieval of account position data. The verb 'Get' and the lack of any modification, deletion, or execution language confirm this is a query operation.
Attacks that exploit this kind of access
Get portfolio positions with market values. It is categorised as a Read tool in the Ib Async MCP Server, which means it retrieves data without modifying state.
Register the Ib Async MCP server in PolicyLayer and add a rule for get_portfolio: 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 Ib Async. Nothing to install.
get_portfolio 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_portfolio 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_portfolio. 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_portfolio is provided by the Ib Async MCP server (nadavgb-atom/ib-async-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 →