read_image
Fetch an image URL and return its bytes for vision analysis by the AI client. Pair with scan_unique_images to inspect images already on the site. After receiving the image, describe it (subject, style, palette, composition, mood, lighting, background, notable_details) to build an image-generation...
This record as markdown: /tools/webcake-storefront/read-image.md
What read_image does on Webcake Storefront
AI agents call read_image to retrieve information from Webcake Storefront without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why read_image is rated Low
This tool retrieves existing image data for analysis purposes only. It has no capability to modify, delete, or execute actions on the storefront or its data. The only potential minor concern is if image URLs could be enumerated to discover private/unpublished content, but the base operation is a simple read.
From the tool's definition Tool description explicitly states 'Fetch an image URL and return its bytes' — a retrieval operation with no modification or side effects. The purpose is vision analysis by the AI client, not data manipulation.
Attacks that exploit this kind of access
The rule that runs read_image safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Webcake Storefront, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For read_image, this is the rule to start with:
read_image is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Webcake Storefront, apply this rule, and every read_image call is checked against it from then on.
Questions about read_image
Fetch an image URL and return its bytes for vision analysis by the AI client. Pair with scan_unique_images to inspect images already on the site. After receiving the image, describe it (subject, style, palette, composition, mood, lighting, background, notable_details) to build an image-generation brief. ${DESCRIBE_HINT}. It is categorised as a Read tool in the Webcake Storefront MCP Server, which means it retrieves data without modifying state.
Register the Webcake Storefront MCP server in PolicyLayer and add a rule for read_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 Webcake Storefront. Nothing to install.
read_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 read_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 read_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.
read_image is provided by the Webcake Storefront MCP server (webcake-storefront-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Webcake Storefront, and thousands of servers like it.
This server
Across the catalogue