Compile Pine Script via TradingView\
AI agents invoke pine_check 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.
Compiling Pine Script is an execution action that runs code through an external application. While it may not directly trade or delete data, it executes arbitrary Pine Script code in TradingView, which could have side effects depending on the script content. The blast radius is medium since it operates within TradingView's sandbox but could trigger alerts or chart changes.
From the tool's definition Compile Pine Script via TradingView — triggers an external compilation/execution operation in the TradingView Desktop app via Chrome DevTools Protocol
Attacks that exploit this kind of access
Compile Pine Script via TradingView\. 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.
Register the Tradingview MCP server in PolicyLayer and add a rule for pine_check: 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.
pine_check 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 pine_check 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 pine_check. 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.
pine_check 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →