annotate_last_image
AI agents use annotate_last_image to create or update resources in Visual Annotation MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Visual Annotation MCP environment.
The tool likely draws/writes annotations on the last captured screenshot image. This is a Write operation as it modifies or overlays data on an existing image. Confidence is low because the description is empty, so we rely on the tool name and server context. Annotations are typically reversible (you can take a new screenshot), so Destructive is unlikely.
From the tool's definition Tool name 'annotate_last_image' and server description mentions 'draw annotations with color contrast selection' on screenshots
Attacks that exploit this kind of access
annotate_last_image. It is categorised as a Write tool in the Visual Annotation MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Visual Annotation MCP server in PolicyLayer and add a rule for annotate_last_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 Visual Annotation MCP. Nothing to install.
annotate_last_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 annotate_last_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 annotate_last_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.
annotate_last_image is provided by the Visual Annotation MCP server (mstocker1/visual_annotation_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 →