close_position
AI agents call close_position to permanently remove resources in Alpaca MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Closing a trading position is a market-executed action that sells or liquidates an open position. This is effectively irreversible once executed (the trade settles in the market). Given the financial trading context of the Alpaca MCP server, this could also qualify as Financial, but since it irreversibly liquidates an asset holding, Destructive is the most appropriate category.
From the tool's definition Tool name 'close_position' on a trading infrastructure server that supports 'stock/options trading, portfolio management' — closing a position liquidates/sells a financial holding irreversibly in the market.
Attacks that exploit this kind of access
close_position. It is categorised as a Destructive tool in the Alpaca MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Alpaca MCP Server MCP server in PolicyLayer and add a rule for close_position: 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 Alpaca MCP Server. Nothing to install.
close_position is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the close_position 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 close_position. 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.
close_position is provided by the Alpaca MCP Server MCP server (jbkix06/alpaca_mcp_server). 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 →