31 tools. 7 can modify or destroy data without limits.
3 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (figma_delete_comment, figma_delete_comment_reaction, figma_delete_webhook) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (figma_post_comment, figma_post_comment_reaction, figma_post_webhook) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
figma_delete_comment:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
figma_post_comment:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
figma_get_comment_reactions:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Figma MCP Server server exposes 3 destructive tools including figma_delete_comment, figma_delete_comment_reaction, figma_delete_webhook. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Figma MCP Server server has 4 write tools including figma_post_comment, figma_post_comment_reaction, figma_post_webhook. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
31 tools across 3 categories: Destructive, Read, Write. 24 are read-only. 7 can modify, create, or delete data.
One line change. Instead of running the Figma MCP Server server directly, prefix it with Intercept: intercept -c thirdstrandstudio-mcp-figma.yaml -- npx -y @thirdstrandstudio/mcp-figma. Download a pre-built policy from policylayer.com/policies/thirdstrandstudio-mcp-figma and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.