AI agents use set_brush_size 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 changes drawing configuration parameters that influence how subsequent strokes appear on the canvas. It is a reversible modification with no permanent data loss or external side effects—the brush size can be changed again or the canvas can be cleared. It does not execute arbitrary code, delete data, or commit financial transactions.
From the tool's definition Tool modifies canvas state by adjusting brush parameters ('Set the brush/stroke size'), which affects subsequent drawing operations but is reversible and non-destructive.
Attacks that exploit this kind of access
Set the brush/stroke size (1-50 pixels). 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_size: 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_size 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_size 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_size. 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_size 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 →