AI agents call get_account_values 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 only queries and retrieves account data (balance, margin) with no side effects, modifications, or execution of trades. It is a read-only operation that fits the Read category. Severity is low because account information disclosure, while sensitive, does not directly enable financial harm or data destruction without additional tools.
From the tool's definition Tool name is 'get_account_values' and description states 'Get account values (balance, margin, etc.)' — retrieves account information without modifying or executing actions.
Attacks that exploit this kind of access
Get account values (balance, margin, etc.). 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_account_values: 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_account_values 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_account_values 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_account_values. 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_account_values 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 →