AI agents invoke replay_step to trigger actions in TradingView MCP Bridge. 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.
This tool drives an action in the TradingView Desktop application via Chrome DevTools Protocol, advancing the chart replay state. It is an external operation that changes application state, making it Execute. The blast radius is low since it only moves a chart view forward one bar and does not modify data, execute trades, or delete anything.
From the tool's definition 'Advance one bar in replay mode' — triggers an external operation (stepping forward in TradingView's replay mode) that affects the state of the running application
Documented attack patterns abuse exactly the kind of access replay_step gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TradingView MCP Bridge, and nothing reaches the server without passing your rules. This is the rule we recommend for replay_step:
{
"version": "1",
"default": "deny",
"tools": {
"replay_step": {
"limits": [
{
"counter": "replay_step_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} 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.
Free to start. No card required.
Advance one bar in replay mode. It is categorised as a Execute tool in the TradingView MCP Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TradingView MCP Bridge 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 MCP Bridge. Nothing to install.
replay_step is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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.
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.
replay_step is provided by the TradingView MCP Bridge MCP server (tradesdontlie/tradingview-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 78 TradingView MCP Bridge tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
78 TradingView MCP Bridge tools catalogued and risk-classified — across an index of 42,500+ MCP servers.