Set guides on a page in Figma. Replaces all existing guides on the page.
AI agents use set_guide to create or update resources in Claude Talk to Figma MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Talk to Figma MCP environment.
The tool creates or modifies design guides within a Figma page. While 'replaces all existing guides' could be interpreted as destructive in scope, guides are non-essential metadata elements that can be easily recreated or restored, making this a reversible Write operation rather than Destructive.
From the tool's definition Tool description states it 'Set guides on a page in Figma. Replaces all existing guides on the page.' This modifies design document content by replacing guides, which is a reversible write operation.
Documented attack patterns abuse exactly the kind of access set_guide gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Talk to Figma MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for set_guide:
{
"version": "1",
"default": "deny",
"tools": {
"set_guide": {
"limits": [
{
"counter": "set_guide_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} set_guide 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 guides on a page in Figma. Replaces all existing guides on the page. It is categorised as a Write tool in the Claude Talk to Figma MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Talk to Figma MCP server in PolicyLayer and add a rule for set_guide: 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 Claude Talk to Figma MCP. Nothing to install.
set_guide 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 set_guide 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 set_guide. 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.
set_guide is provided by the Claude Talk to Figma MCP server (arinspunk/claude-talk-to-figma-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Talk to Figma MCP, 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.
93 Claude Talk to Figma MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.