generate_image
Generate an AI image via kie.ai and return its public R2 URL. Use to mint reusable URLs for content blocks (image, gallery), product photos, or any field that takes an image URL — does NOT attach to a post by itself. Costs credits (see list_image_models). On poll timeout the job continues running...
This record as markdown: /tools/io-favcrm-favcrm/generate-image.md
What generate_image does on FavCRM
AI agents use generate_image to create or update resources in FavCRM, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FavCRM environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
seed | integer | — | Random seed for reproducible output |
prompt | string | Yes | Generation prompt |
modelCode | string | Yes | Image model code from list_image_models |
aspectRatio | string | — | Output aspect ratio (e.g. 16:9, 1:1) |
pollTimeoutMs | integer | — | Default 60000. |
negativePrompt | string | — | Things to exclude from generation |
pollIntervalMs | integer | — | Default 3000. |
Parameters from the server's own tool schema.
Why generate_image is rated Medium
An AI agent can call generate_image faster than any human can review: one bad instruction and it creates or modifies resources in FavCRM by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs generate_image safely
PolicyLayer is an MCP gateway: it sits between your AI agents and FavCRM, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For generate_image, this is the rule to start with:
generate_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 FavCRM, apply this rule, and every generate_image call is checked against it from then on.
Questions about generate_image
Generate an AI image via kie.ai and return its public R2 URL. Use to mint reusable URLs for content blocks (image, gallery), product photos, or any field that takes an image URL — does NOT attach to a post by itself. Costs credits (see list_image_models). On poll timeout the job continues running; pass jobId from the response to merchant ai-media APIs to retrieve it later. It is categorised as a Write tool in the FavCRM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
generate_image accepts 7 parameters: seed, prompt, modelCode, aspectRatio, pollTimeoutMs, negativePrompt, pollIntervalMs. Required: prompt, modelCode. The full parameter table on this page comes from the server's own tool schema.
Register the FavCRM MCP server in PolicyLayer and add a rule for generate_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 FavCRM. Nothing to install.
generate_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_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_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_image is provided by the FavCRM MCP server (https://api.favcrm.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on FavCRM, and thousands of servers like it.
This server
Across the catalogue