ui_evaluate · TradingView MCP: Risk & Policy

WHAT IT DOES

What ui_evaluate does on TradingView MCP

AI agents invoke ui_evaluate to trigger actions in TradingView MCP. 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 ui_evaluate needs a policy

This tool permits arbitrary JavaScript execution within the TradingView application context, which can manipulate charts, access trading data, modify alerts, trigger trades, and exfiltrate sensitive information. The blast radius is critical because an AI agent could execute malicious code that affects financial decision-making, modifies trading parameters, or accesses sensitive market data.

From the tool's definition Tool description explicitly states 'Execute JavaScript code in the TradingView page context' - direct code execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ui_evaluate Rate-limited

ui_evaluate 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": {
    "ui_evaluate": {
      "limits": [
        {
          "counter": "ui_evaluate_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 TradingView MCP, so you can run agents against it safely.

FAQ

Questions about ui_evaluate

What does the ui_evaluate tool do? +

Execute JavaScript code in the TradingView page context for advanced automation. It is categorised as a Execute tool in the TradingView MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ui_evaluate? +

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

What risk level is ui_evaluate? +

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

Can I rate-limit ui_evaluate? +

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

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

ui_evaluate is provided by the TradingView MCP server (ulianbass/tradingview-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.