Resize an image and save to a new file
AI agents use resize_image to create or update resources in image-reader MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your image-reader MCP Server environment.
The tool creates and writes new image data to disk, which is a reversible modification. While it modifies an image, the original file remains untouched and the operation can be undone by deleting the new file. This qualifies as Write rather than Destructive (no deletion/overwrite) or Read (actively creates new data).
From the tool's definition Tool description explicitly states 'Resize an image and save to a new file' — this creates a new file with modified image data.
Attacks that exploit this kind of access
Resize an image and save to a new file. It is categorised as a Write tool in the image-reader MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the image-reader MCP Server MCP server in PolicyLayer and add a rule for resize_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 image-reader MCP Server. Nothing to install.
resize_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 resize_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 resize_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.
resize_image is provided by the image-reader MCP Server MCP server (rupeedev/mcp-image-reader). 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 →