AI agents call what_if_order 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 performs a read-only query of margin impact calculations. The explicit constraint 'without placing order' confirms no side effects occur—it does not create, modify, delete, or execute trades. It retrieves hypothetical margin data for analysis only, making it a Read category tool with low severity since it poses minimal risk if misused by an AI agent.
From the tool's definition Tool name 'what_if_order' and description 'Check margin impact without placing order' indicate a simulation/calculation that retrieves margin information without executing any trades or modifying account state.
Attacks that exploit this kind of access
Check margin impact without placing order. 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 what_if_order: 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.
what_if_order 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 what_if_order 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 what_if_order. 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.
what_if_order 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 →