create_variation
Add a variation (size, color, etc.) to an existing product.
This record as markdown: /tools/io-favcrm-favcrm/create-variation.md
What create_variation does on FavCRM
AI agents use create_variation 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 |
|---|---|---|---|
sku | string | — | Variation SKU |
name | string | — | Variation name |
price | string | Yes | Price as decimal string (e.g. "29.99") |
productId | number | Yes | The product ID |
memberPrice | string | — | Members-only price |
stockStatus | string | — | Stock status |
discountPrice | string | — | Discounted price |
stockQuantity | number | — | Stock quantity |
selectedOptions | object | — | Option selections e.g. {"Size": "Large"} |
Parameters from the server's own tool schema.
Why create_variation is rated Medium
This tool creates new data (product variations) in a reversible manner. It does not execute arbitrary code, delete data irreversibly, move money, or retrieve sensitive information. The operation is a standard database write that can be undone by deleting the variation. Blast radius is minimal—misconfiguration adds unwanted product options but causes no financial loss or irreversible harm.
From the tool's definition Tool name 'create_variation' and description 'Add a variation (size, color, etc.) to an existing product' indicate the tool creates a new product attribute variant.
Attacks that exploit this kind of access
The rule that runs create_variation 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 create_variation, this is the rule to start with:
create_variation 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 create_variation call is checked against it from then on.
Questions about create_variation
Add a variation (size, color, etc.) to an existing product. 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.
create_variation accepts 9 parameters: sku, name, price, productId, memberPrice, stockStatus, discountPrice, stockQuantity, selectedOptions. Required: price, productId. 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 create_variation: 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.
create_variation 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 create_variation 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 create_variation. 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.
create_variation 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