generate_site_image
AI-GENERATE an image for a site (server-side ComfyUI pipeline; no external image needed). Describe the image in the prompt (English works best), get back a permanent CDN URL. Generation is synchronous and takes 20–60 seconds — generate images ONE AT A TIME, never in parallel. The returned image.u...
This record as markdown: /tools/a3plus-mcp/generate-site-image.md
What generate_site_image does on A3plus
AI agents use generate_site_image to create or update resources in A3plus, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A3plus environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
alt | string | — | Short literal description of the image content (≤ 500 chars) — stored as the asset alt text. |
kind | string | — | What the image is for — sets the canvas size. Default: article. |
prompt | string | Yes | Image description (≤ 2000 chars). Concrete visual language works best: subject, setting, style, lighting. Avoid asking for text/words in the image — text render |
siteId | string | Yes | The A3Plus site ID this image is for. |
negativePrompt | string | — | Optional: things to avoid. A strong default (no text/watermarks/low quality) is applied when omitted. |
Parameters from the server's own tool schema.
Why generate_site_image is rated Medium
An AI agent can call generate_site_image faster than any human can review: one bad instruction and it creates or modifies resources in A3plus by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs generate_site_image safely
PolicyLayer is an MCP gateway: it sits between your AI agents and A3plus, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For generate_site_image, this is the rule to start with:
generate_site_image stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect A3plus, apply this rule, and every generate_site_image call is checked against it from then on.
Questions about generate_site_image
AI-GENERATE an image for a site (server-side ComfyUI pipeline; no external image needed). Describe the image in the prompt (English works best), get back a permanent CDN URL. Generation is synchronous and takes 20–60 seconds — generate images ONE AT A TIME, never in parallel. The returned image.url is applied with the existing tools: kind "hero" → update_site_branding { hero: { url } }; kind "article" → update_article featuredImageUrl or replace an <img>/markdown URL inside content; "logo" → update_site_branding { logo: { url } }. Typical bulk-fix loop for a site with bad/odd images: list_articles → get_article (inspect image URLs) → generate_site_image with a prompt matching the article topic → update_article swapping the old URL for the new one → next article. kind sets the canvas: hero/article 1280×768 (wide), about 1024×768, logo 512×512, generic 1024×1024. Always pass alt — a short literal description of the image content — it is stored with the asset and should also be used as the img alt text (SEO). It is categorised as a Write tool in the A3plus MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
generate_site_image accepts 5 parameters: alt, kind, prompt, siteId, negativePrompt. Required: prompt, siteId. The full parameter table on this page comes from the server's own tool schema.
Register the A3plus MCP server in PolicyLayer and add a rule for generate_site_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 A3plus. Nothing to install.
generate_site_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 generate_site_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 generate_site_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.
generate_site_image is provided by the A3plus MCP server (a3plus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on A3plus, and thousands of servers like it.
This server
Across the catalogue