AI agents use stability_image_to_image to create or update resources in UnClick — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UnClick environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
steps | number | — | |
prompt | string | Yes | |
api_key | string | Yes | |
samples | number | — | |
strength | number | — | 0.0-1.0: how much to change the image (default: 0.35) |
cfg_scale | number | — | |
engine_id | string | — | |
image_url | string | Yes | URL of the source image |
negative_prompt | string | — |
Parameters from the server's own tool schema.
This tool modifies an existing image by applying a text-guided transformation, creating a new output. It is a Write operation as it produces/modifies content. It does not execute code, delete data, or involve financial transactions. Misuse could involve generating inappropriate imagery, but the blast radius is limited to image content generation.
From the tool's definition Transform an existing image using a text prompt
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
Transform an existing image using a text prompt with Stability AI. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
stability_image_to_image accepts 9 parameters: steps, prompt, api_key, samples, strength, cfg_scale, engine_id, image_url, negative_prompt. Required: prompt, api_key, image_url. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for stability_image_to_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 UnClick. Nothing to install.
stability_image_to_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 stability_image_to_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 stability_image_to_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.
stability_image_to_image is provided by the UnClick MCP server (@unclick/mcp-server). 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 →