AI agents use merge_images 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 creates or modifies image data by combining multiple images into a single output file. It is a reversible write operation (the original images remain unchanged, and the merged result can be deleted or regenerated). It does not execute arbitrary code, delete data irreversibly, or move money. The local-only operation and non-destructive nature keep severity low.
From the tool's definition Tool description states it 'Merge[s] multiple images into a single image' — a creation/modification operation that produces new image output.
Attacks that exploit this kind of access
Merge multiple images into a single image by arranging them horizontally, vertically, or in a grid. 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 merge_images: 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.
merge_images 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 merge_images 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 merge_images. 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.
merge_images 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 →