Get fills/executions for a specific order
AI agents call getExecutions to retrieve information from TradeStation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about completed order executions/fills. It queries existing data with no side effects—no money moves, no orders are created/modified/cancelled, and no data is deleted or overwritten. While it is part of a trading system, the tool itself only reads execution history.
From the tool's definition Tool name 'getExecutions' and description 'Get fills/executions for a specific order' indicate a read-only query operation that retrieves historical execution data without modifying any state.
Attacks that exploit this kind of access
Get fills/executions for a specific order. It is categorised as a Read tool in the TradeStation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the TradeStation MCP Server MCP server in PolicyLayer and add a rule for getExecutions: 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 TradeStation MCP Server. Nothing to install.
getExecutions 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 getExecutions 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 getExecutions. 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.
getExecutions is provided by the TradeStation MCP Server MCP server (maven81g/tradestation_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 →