AI agents call get_pnl 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 account performance metrics (profit/loss data) without modifying any positions, executing trades, or affecting financial instruments. It is purely informational and has no side effects. Even in the context of a trading platform, querying PnL is a read-only operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'get_pnl' and description 'Get profit and loss' indicate a data retrieval operation. The verb 'get' combined with a query-like function (retrieving PnL metrics) shows no data modification, deletion, or execution of trades.
Attacks that exploit this kind of access
Get profit and loss. 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_pnl: 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_pnl 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_pnl 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_pnl. 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_pnl 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 →