Set Pine Script source code in the editor
AI agents use pine_set_source to create or update resources in Tradingview — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tradingview environment.
The tool directly modifies Pine Script source code in the editor. While this is reversible (code can be edited again), it's categorized as Write rather than Execute because it only stores/modifies the code itself without triggering execution.
From the tool's definition Tool name 'pine_set_source' and description 'Set Pine Script source code in the editor' indicates writing/modifying code in the TradingView Pine Script editor. This is a Write operation that modifies code reversibly.
Attacks that exploit this kind of access
Set Pine Script source code in the editor. It is categorised as a Write tool in the Tradingview MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tradingview MCP server in PolicyLayer and add a rule for pine_set_source: 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_set_source is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the pine_set_source 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_set_source. 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_set_source 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 →