Batch convert all images in a folder to AVIF or WebP format
AI agents invoke convert_folder to trigger actions in Image Converter. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool performs a batch operation that runs ImageMagick conversions across all images in a folder. It triggers an external image processing operation at scale, and may overwrite original files or produce large numbers of output files depending on implementation. The batch nature means a misconfigured call could affect many files at once, raising the blast radius.
From the tool's definition Batch convert all images in a folder to AVIF or WebP format
Attacks that exploit this kind of access
Batch convert all images in a folder to AVIF or WebP format. It is categorised as a Execute tool in the Image Converter MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Image Converter MCP server in PolicyLayer and add a rule for convert_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 Image Converter. Nothing to install.
convert_folder is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the convert_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 convert_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.
convert_folder is provided by the Image Converter MCP server (pratham9467/image-converter-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 →