AI agents use convert_image to create or update resources in Imagic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Imagic environment.
Converting an image format is a reversible write operation that creates or transforms data. The operation does not delete the original file, execute arbitrary code, move money, or cause irreversible damage. Since it runs locally with no uploads, the blast radius of misuse is limited to the local system.
From the tool's definition Tool description states 'Convert an image to a different format (PNG, JPEG, GIF, WebP, or ICO)' — this creates or modifies image files in a new format.
Attacks that exploit this kind of access
Convert an image to a different format (PNG, JPEG, GIF, WebP, or ICO). It is categorised as a Write tool in the Imagic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Imagic MCP server in PolicyLayer and add a rule for convert_image: 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 Imagic. Nothing to install.
convert_image 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 convert_image 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 convert_image. 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.
convert_image is provided by the Imagic MCP server (sonic0002/imagic-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 →