Draw a circle. thickness=-1 fills.
AI agents use draw_circle to create or update resources in farshid-mcp-imageProcessing — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your farshid-mcp-imageProcessing environment.
This tool writes/modifies image data by drawing a circle onto an existing image. It is reversible in the sense that the original image can be preserved, but it does alter image content. No code execution, deletion, or financial action is involved. Blast radius is low as it only affects local image files.
From the tool's definition 'Draw a circle. thickness=-1 fills.' — modifies an image by drawing onto it.
Attacks that exploit this kind of access
Draw a circle. thickness=-1 fills. It is categorised as a Write tool in the farshid-mcp-imageProcessing MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the farshid-mcp-imageProcessing MCP server in PolicyLayer and add a rule for draw_circle: 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 farshid-mcp-imageProcessing. Nothing to install.
draw_circle 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_circle 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_circle. 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_circle is provided by the farshid-mcp-imageProcessing MCP server (pirahansiah/farshid-mcp-imageprocessing). 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 →