run_scanner · Ib Async MCP: Risk & Policy

WHAT IT DOES

What run_scanner does on Ib Async

AI agents invoke run_scanner to trigger actions in Ib Async. 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.

WHY IT NEEDS A POLICY

Why run_scanner needs a policy

Running a market scanner initiates an external operation via the IB API that queries real-time market data and returns results. It is not purely a passive read (it triggers an active scanner job on the broker's infrastructure), placing it in Execute. It does not move money or delete data, so Financial and Destructive do not apply.

From the tool's definition 'Run a market scanner' — actively triggers an external operation against the Interactive Brokers API to execute a scanner query

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_scanner Rate-limited

run_scanner 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_scanner": {
      "limits": [
        {
          "counter": "run_scanner_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about run_scanner

What does the run_scanner tool do? +

Run a market scanner. It is categorised as a Execute tool in the Ib Async MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_scanner? +

Register the Ib Async MCP server in PolicyLayer and add a rule for run_scanner: 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.

What risk level is run_scanner? +

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

Can I rate-limit run_scanner? +

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

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

run_scanner 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.