close_all_positions · Alpaca MCP: Risk & Policy

WHAT IT DOES

What close_all_positions does on Alpaca

AI agents use close_all_positions to create or update resources in Alpaca — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Alpaca environment.

WHY IT NEEDS A POLICY

Why close_all_positions needs a policy

An AI agent can call close_all_positions faster than any human can review — one bad instruction and it creates or modifies resources in Alpaca by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

close_all_positions Rate-limited

close_all_positions stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "close_all_positions": {
      "limits": [
        {
          "counter": "close_all_positions_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Alpaca, so you can run agents against it safely.

FAQ

Questions about close_all_positions

What does the close_all_positions tool do? +

Closes all open positions. It is categorised as a Write tool in the Alpaca MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on close_all_positions? +

Register the Alpaca MCP server in PolicyLayer and add a rule for close_all_positions: 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. Nothing to install.

What risk level is close_all_positions? +

close_all_positions is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit close_all_positions? +

Yes. Add a rate_limit block to the close_all_positions 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.

How do I block close_all_positions completely? +

Set action: deny in the PolicyLayer policy for close_all_positions. 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 MCP server provides close_all_positions? +

close_all_positions is provided by the Alpaca MCP server (mfoster5303-1/alpaca-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.