Remove all drawings from the chart
AI agents call draw_clear to permanently remove resources in TradingView MCP Jackson — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This action destroys data (chart drawings/annotations) that cannot be automatically recovered. While chart state might be restorable from session history, the tool itself performs a permanent erasure operation with no undo mechanism built into its contract. This qualifies as Destructive rather than Write (which is reversible).
From the tool's definition Tool explicitly performs 'Remove all drawings from the chart', which irreversibly deletes user-created chart annotations and technical analysis work.
Attacks that exploit this kind of access
Remove all drawings from the chart. It is categorised as a Destructive tool in the TradingView MCP Jackson MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the TradingView MCP Jackson MCP server in PolicyLayer and add a rule for draw_clear: 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 Jackson. Nothing to install.
draw_clear is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the draw_clear 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 draw_clear. 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.
draw_clear is provided by the TradingView MCP Jackson MCP server (nimit791/tradingview-mcp-jackson). 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 →