Set the value of an existing variable for a specific mode, or bind a variable to a node property.
AI agents use figma_set_variable to create or update resources in Figma MCP Bridge — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Figma MCP Bridge environment.
This tool creates or modifies variable bindings and values within a Figma document. It is reversible—variable values can be changed back, and bindings can be rebound. This is a Write operation rather than Read (which would only retrieve values).
From the tool's definition Tool description states 'Set the value of an existing variable' and 'bind a variable to a node property', which are modification operations.
Documented attack patterns abuse exactly the kind of access figma_set_variable gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Figma MCP Bridge, and nothing reaches the server without passing your rules. This is the rule we recommend for figma_set_variable:
{
"version": "1",
"default": "deny",
"tools": {
"figma_set_variable": {
"limits": [
{
"counter": "figma_set_variable_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} figma_set_variable 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.
Free to start. No card required.
Set the value of an existing variable for a specific mode, or bind a variable to a node property. It is categorised as a Write tool in the Figma MCP Bridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Figma MCP Bridge MCP server in PolicyLayer and add a rule for figma_set_variable: 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 Figma MCP Bridge. Nothing to install.
figma_set_variable 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 figma_set_variable 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 figma_set_variable. 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.
figma_set_variable is provided by the Figma MCP Bridge MCP server (magic-spells/figma-mcp-bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Figma MCP Bridge, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
88 Figma MCP Bridge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.