High Risk →

ibkr_preview_order

Run IBKR what-if analysis for an order and return margin/commission impact.

How to control ibkr_preview_order ↓

What ibkr_preview_order does on Ibkr

AI agents invoke ibkr_preview_order to trigger actions in Ibkr. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

High Risk

Why ibkr_preview_order needs a policy

This is Execute rather than Write because it runs a simulation/analysis operation whose effects depend on the order parameters provided. However, it is high severity because misuse could allow an agent to reverse-engineer optimal harmful trading strategies, probe margin requirements to identify liquidation triggers, or discover market manipulation opportunities.

From the tool's definition Tool executes a what-if analysis ('Run IBKR what-if analysis') on Interactive Brokers, which is a real-time operation that triggers external computation and risk modeling on the financial system, even though it does not commit the order.

Documented attack patterns abuse exactly the kind of access ibkr_preview_order gives an agent:

How to control ibkr_preview_order

PolicyLayer is an MCP gateway — it sits between your AI agents and Ibkr, and nothing reaches the server without passing your rules. This is the rule we recommend for ibkr_preview_order:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "ibkr_preview_order": {
      "limits": [
        {
          "counter": "ibkr_preview_order_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

ibkr_preview_order stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Ibkr — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about ibkr_preview_order

What does the ibkr_preview_order tool do? +

Run IBKR what-if analysis for an order and return margin/commission impact. It is categorised as a Execute tool in the Ibkr MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ibkr_preview_order? +

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

What risk level is ibkr_preview_order? +

ibkr_preview_order is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ibkr_preview_order? +

Yes. Add a rate_limit block to the ibkr_preview_order 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 ibkr_preview_order completely? +

Set action: deny in the PolicyLayer policy for ibkr_preview_order. 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 ibkr_preview_order? +

ibkr_preview_order is provided by the Ibkr MCP server (patrickpxp/ibkr-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Ibkr tool call.

Start from Ibkr, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

33 Ibkr tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.