Display an image from the filesystem. Returns the image as base64 data that Claude can render.
AI agents call display-image to retrieve information from Image Viewer MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the filesystem to retrieve image content and encode it for display. There are no modifications to data, no code execution, no deletions, and no financial implications. The only action is retrieving and presenting existing image files, making it a straightforward Read category tool with minimal security risk.
From the tool's definition Tool 'display-image' retrieves and returns image data as base64 without modification or side effects. Description states it 'Display an image from the filesystem' and 'Returns the image as base64 data' — a pure read operation.
Attacks that exploit this kind of access
Display an image from the filesystem. Returns the image as base64 data that Claude can render. It is categorised as a Read tool in the Image Viewer MCP MCP Server, which means it retrieves data without modifying state.
Register the Image Viewer MCP server in PolicyLayer and add a rule for display-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 Viewer MCP. Nothing to install.
display-image is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the display-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 display-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.
display-image is provided by the Image Viewer MCP server (itrimble/image-viewer-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 →