Replace ALL points of an existing drawing at once. Point count must match what the shape type expects (1 for horizontal_line, 2 for trend/fib, 3 for pitchfork).
AI agents use draw_update_points to create or update resources in TradingView MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TradingView MCP environment.
This tool updates drawing objects (modifying point coordinates) rather than reading data or executing arbitrary commands. It is reversible (drawings can be modified again or deleted), so it does not qualify as Destructive. It does not execute code or trigger external side effects, so it is not Execute. It falls under Write because it modifies chart drawing state in a controlled, non-destructive manner.
From the tool's definition The tool description states 'Replace ALL points of an existing drawing at once,' which modifies existing data (drawing objects) on the chart. This is a modification operation that changes the state of drawings but is reversible—points can be redrawn or undone.
Attacks that exploit this kind of access
Replace ALL points of an existing drawing at once. Point count must match what the shape type expects (1 for horizontal_line, 2 for trend/fib, 3 for pitchfork). It is categorised as a Write tool in the TradingView MCP 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 draw_update_points: 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.
draw_update_points 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 draw_update_points 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_update_points. 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_update_points 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.
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 →