replay_start · TradingView MCP: Risk & Policy

WHAT IT DOES

What replay_start does on TradingView MCP

AI agents invoke replay_start 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 replay_start needs a policy

This tool executes a specific operational mode (bar replay) that changes the state and behavior of the trading platform. While it doesn't execute arbitrary code or delete data, it does trigger a complex external operation whose effects depend on the provided date argument. The ability to start replay mode at specific dates could be misused to artificially generate misleading trading signals or practice scenarios.

From the tool's definition "Start bar replay mode" - initiates an automated operation that triggers TradingView's replay functionality, which simulates historical market replay and involves running automated trading practice scenarios.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

replay_start Rate-limited

replay_start 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_start": {
      "limits": [
        {
          "counter": "replay_start_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 replay_start

What does the replay_start tool do? +

Start bar replay mode, optionally at a specific date. 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 replay_start? +

Register the TradingView MCP server in PolicyLayer and add a rule for replay_start: 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 replay_start? +

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

Can I rate-limit replay_start? +

Yes. Add a rate_limit block to the replay_start 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_start completely? +

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

replay_start 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.