run_api_test · Shioaji MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_api_test does on Shioaji MCP Server

AI agents invoke run_api_test to trigger actions in Shioaji MCP Server. 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_api_test needs a policy

This tool executes automated tests that include login operations and order tests against a live trading API. While framed as a compliance test, it performs real executable actions against authentication systems and potentially order management. Given the sibling tools include place_order and cancel_order, and this tool performs "order tests", it could trigger side effects on trading accounts.

From the tool's definition Tool description states "Run API test" which involves "login and order tests" - these are executable operations that interact with live trading systems and account authentication.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_api_test Rate-limited

run_api_test 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_api_test": {
      "limits": [
        {
          "counter": "run_api_test_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 Shioaji MCP Server, so you can run agents against it safely.

FAQ

Questions about run_api_test

What does the run_api_test tool do? +

Run API test for service terms compliance (login and order tests). It is categorised as a Execute tool in the Shioaji MCP Server 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_api_test? +

Register the Shioaji MCP Server MCP server in PolicyLayer and add a rule for run_api_test: 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 Shioaji MCP Server. Nothing to install.

What risk level is run_api_test? +

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

Can I rate-limit run_api_test? +

Yes. Add a rate_limit block to the run_api_test 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_api_test completely? +

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

run_api_test is provided by the Shioaji MCP Server MCP server (offbeat-studio/shioaji-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.