AI agents call get_executions 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 execution reports (historical records of trades that have been executed). Retrieving or querying data without modifying, deleting, or triggering new actions is a Read operation. Even though the server connects to Interactive Brokers (a financial platform), this specific tool only fetches information rather than moving money or executing new trades.
From the tool's definition Tool name is 'get_executions' and description states 'Get execution reports.' The verb 'Get' and the read-only nature of retrieving historical execution reports indicate a query operation with no side effects.
Attacks that exploit this kind of access
Get execution reports. 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_executions: 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_executions 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_executions 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_executions. 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_executions 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 →