replay_step · Tradingview MCP: Risk & Policy

WHAT IT DOES

What replay_step does on Tradingview

AI agents invoke replay_step to trigger actions in Tradingview. 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 replay_step needs a policy

This tool drives an action in the TradingView application (stepping forward in replay mode), which is an external operation executed via CDP. It does not read, write, or delete data directly, but triggers a UI/state change in the running app. Severity is low as the blast radius is limited to advancing chart replay by one bar, with no financial, destructive, or persistent side effects.

From the tool's definition 'Advance one bar in replay mode' — triggers an external operation in the TradingView Desktop app via Chrome DevTools Protocol

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

replay_step Rate-limited

replay_step 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": {
    "replay_step": {
      "limits": [
        {
          "counter": "replay_step_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, so you can run agents against it safely.

FAQ

Questions about replay_step

What does the replay_step tool do? +

Advance one bar in replay mode. It is categorised as a Execute tool in the Tradingview MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on replay_step? +

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

What risk level is replay_step? +

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

Can I rate-limit replay_step? +

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

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

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