open_backtest_ui · Nubra MCP Server MCP: Risk & Policy

WHAT IT DOES

What open_backtest_ui does on Nubra MCP Server

AI agents invoke open_backtest_ui to trigger actions in Nubra 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 open_backtest_ui needs a policy

This tool launches an external desktop application and runs strategy backtests, which constitutes executing an external operation. While it doesn't directly modify data or move money, it triggers a desktop UI process and runs computational backtests using live auth state. No destructive or financial side effects are described, but execution of external programs with auth credentials warrants medium severity.

From the tool's definition 'Launch the desktop backtest UI' and 'runs NubraOSS-style strategy backtests' — actively launches a desktop application and executes backtesting operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

open_backtest_ui Rate-limited

open_backtest_ui 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": {
    "open_backtest_ui": {
      "limits": [
        {
          "counter": "open_backtest_ui_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 Nubra MCP Server, so you can run agents against it safely.

FAQ

Questions about open_backtest_ui

What does the open_backtest_ui tool do? +

Launch the desktop backtest UI. It reuses the current Nubra MCP auth state and runs NubraOSS-style strategy backtests using Nubra historical data only. It is categorised as a Execute tool in the Nubra 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 open_backtest_ui? +

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

What risk level is open_backtest_ui? +

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

Can I rate-limit open_backtest_ui? +

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

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

open_backtest_ui is provided by the Nubra MCP Server MCP server (socials-zanskar/nubra-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.