AI agents use draw_line to create or update resources in Paint MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Paint MCP environment.
The tool modifies canvas state by adding visual content, which is a write operation. It is not destructive because the changes are reversible using existing canvas operations. It has minimal blast radius—an incorrect line placement affects only the local drawing buffer, not external systems or data. Severity is low because erroneous lines are easily corrected without data loss or operational impact.
From the tool's definition Tool creates and modifies pixel data on the canvas through line drawing: 'Draw a line from (x1, y1) to (x2, y2)'. This is a reversible modification (canvas can be cleared via clear_canvas or drawn over) with no permanent destruction or external side effects.
Attacks that exploit this kind of access
Draw a line from (x1, y1) to (x2, y2). It is categorised as a Write tool in the Paint MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Paint MCP server in PolicyLayer and add a rule for draw_line: 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 Paint MCP. Nothing to install.
draw_line 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_line 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_line. 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_line is provided by the Paint MCP server (joeyballentine/paint-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 →