AI agents use set_brush_shape 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.
This tool modifies the brush shape parameter, which is a reversible configuration change to the drawing state. It does not execute arbitrary code, delete data, or cause financial transactions. It has low blast radius—misconfiguring a brush shape produces a visual artifact that can be undone (e.g., by clearing the canvas or changing the brush again).
From the tool's definition Tool name 'set_brush_shape' and server context (Pygame-based drawing canvas) indicate this modifies brush configuration state.
Attacks that exploit this kind of access
set_brush_shape. 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 set_brush_shape: 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.
set_brush_shape 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 set_brush_shape 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 set_brush_shape. 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.
set_brush_shape 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 →