generate_variants
Generates variants of existing screens within a project using a text prompt. Instructions for Tool Call: * If the tool fails with a timeout, don't retry. Instead, try to get the screen with get_screen method every 30 seconds for up to 10 times before giving up.
This record as markdown: /tools/com-googleapis-stitch-mcp/generate-variants.md
What generate_variants does on Mcp
AI agents use generate_variants to create or update resources in Mcp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Yes | Required. The input text used to generate the variants. |
modelId | string | — | Optional. The model to use for generation. |
projectId | string | Yes | Required. The project ID of screens to generate variants for, example: '4044680601076201931', without the `projects/` prefix. |
deviceType | string | — | Optional. The type of device that captured the screenshot, e.g., mobile or desktop. |
variantOptions | object | Yes | Required. The variant options for generation, including the number of variants, creative range, and aspects to focus on. |
selectedScreenIds | array | Yes | Required. The screen ids of screen to generate variants for, example: ['98b50e2ddc9943efb387052637738f61', '98b50e2ddc9943efb387052637738f62'], without the `scr |
Parameters from the server's own tool schema.
Why generate_variants is rated Medium
An AI agent can call generate_variants faster than any human can review: one bad instruction and it creates or modifies resources in Mcp by the hundred, each call as confident as the last.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs generate_variants safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For generate_variants, this is the rule to start with:
generate_variants 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 Mcp, apply this rule, and every generate_variants call is checked against it from then on.
Questions about generate_variants
Generates variants of existing screens within a project using a text prompt. Instructions for Tool Call: * If the tool fails with a timeout, don't retry. Instead, try to get the screen with get_screen method every 30 seconds for up to 10 times before giving up. It is categorised as a Write tool in the Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
generate_variants accepts 6 parameters: prompt, modelId, projectId, deviceType, variantOptions, selectedScreenIds. Required: prompt, projectId, variantOptions, selectedScreenIds. The full parameter table on this page comes from the server's own tool schema.
Register the MCP server in PolicyLayer and add a rule for generate_variants: 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 Mcp. Nothing to install.
generate_variants 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_variants 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_variants. 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_variants is provided by the MCP server (https://stitch.googleapis.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on , and thousands of servers like it.
This server
Across the catalogue