Host an image (chart, photo, diagram) on lightpaper and get back a permanent https URL.
AI agents use upload_image to create or update resources in Lightpaper Mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lightpaper Mcp environment.
This tool creates new data (hosting an image) and generates a permanent URL reference, which is a reversible write operation. The image can typically be deleted or replaced. It is not destructive (no irreversible deletion), not financial, and not arbitrary code execution.
From the tool's definition Tool 'upload_image' description states 'Host an image...and get back a permanent https URL', indicating creation and storage of new data on a persistent platform.
Attacks that exploit this kind of access
Host an image (chart, photo, diagram) on lightpaper and get back a permanent https URL. It is categorised as a Write tool in the Lightpaper Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lightpaper MCP server in PolicyLayer and add a rule for upload_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 Lightpaper Mcp. Nothing to install.
upload_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 upload_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 upload_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.
upload_image is provided by the Lightpaper MCP server (pypi:lightpaper-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 →