AI agents use process_folder 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.
This tool batch-processes all images in a folder, modifying or creating image files. It writes/overwrites output files but is not explicitly described as irreversible deletion. However, if it overwrites originals in-place, effects could be hard to reverse — but the description does not confirm destructive overwriting, so Write is the most appropriate category.
From the tool's definition Apply a convert, resize, or convert-and-resize operation to all image files in a folder
Attacks that exploit this kind of access
Apply a convert, resize, or convert-and-resize operation to all image files in a folder. Non-image files are automatically skipped. 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 process_folder: 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.
process_folder 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 process_folder 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 process_folder. 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.
process_folder 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 →