vlm_edit_image
AI agents use vlm_edit_image to create or update resources in Albumentations — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Albumentations environment.
The tool name 'vlm_edit_image' indicates modification of image data. Within an image augmentation server (Albumentations), this most likely creates or modifies images reversibly rather than permanently deleting them. Without a description, confidence is reduced, but the context strongly suggests Write-category functionality (image manipulation).
From the tool's definition Tool name 'vlm_edit_image' combined with server context showing image augmentation/transformation capabilities (blur, rotation, transforms). Description is empty, limiting confidence.
Attacks that exploit this kind of access
vlm_edit_image. It is categorised as a Write tool in the Albumentations MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Albumentations MCP server in PolicyLayer and add a rule for vlm_edit_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 Albumentations. Nothing to install.
vlm_edit_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 vlm_edit_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 vlm_edit_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.
vlm_edit_image is provided by the Albumentations MCP server (ramsi-k/albumentations-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 →