// SCAN REPORT

Sunnyside Figma MCP

31 tools. 3 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

3 can modify or destroy data

28 read-only

31 tools total

Community server · catalogue entry verified 11/06/2026

How to control Sunnyside Figma MCP ↓

TOOL MAP

Read (28) Write / Execute (2) Destructive / Financial (1)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High apply_token_change The tool modifies actual files with changes that cannot be trivially undone (requires explicit rollback), making it irreversible in practical terms. Write · Medium generate_codegen_plugin The tool generates codegen plugin configurations or code files, which represents data creation/modification. Write · Medium generate_migration_code This tool creates new code artifacts (migration scripts, updated CSS, modified components, test cases) that alter the codebase.

3 of Sunnyside Figma MCP's 31 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL SUNNYSIDE FIGMA MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Sunnyside Figma MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "apply_token_change": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "generate_codegen_plugin": {
    "limits": [
      {
        "counter": "generate_codegen_plugin_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "build_dependency_graph": {
    "limits": [
      {
        "counter": "build_dependency_graph_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Sunnyside Figma MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SUNNYSIDE FIGMA →

Free to start. No card required.

ALL 31 SUNNYSIDE FIGMA MCP TOOLS

DESTRUCTIVE 1 tools

Destructive apply_token_change Apply a previously simulated token change to the actual files. Cannot be undone without rollback.

WRITE 2 tools

Write generate_codegen_plugin Generate a proper Figma Dev Mode codegen plugin following official standards Write generate_migration_code Generate comprehensive migration code for design token changes, including CSS updates, component modifications

READ 28 tools

Read build_dependency_graph Scan codebase and build dependency graph mapping design token usage across files. This is the foundation for i Read analyze_app_structure Perform comprehensive analysis of entire app structure, extracting detailed information from all pages and key Read analyze_figma_components Analyze component library usage and organization in a Figma file Read analyze_token_change_impact AI-powered analysis of what happens when a design token changes. Identifies affected components, edge cases, a Read batch_extract_frames Extract detailed CSS, layout, and component information from multiple frames at once Read check_figma_dev_connection Check if Figma Read debug_token_registry Debug tool to check what tokens are currently stored in the design token registry Read download_figma_images Download SVG and PNG images from Figma. Use get_JSON first to get the file key from plugin data. Read extract_design_tokens Extract and catalog design tokens from current Figma selection. Maps colors, spacing, typography to create the Read get_All_Layers_CSS Get comprehensive CSS for all layers from the latest Figma extraction (like Figma Read get_Basic_CSS Get basic CSS for the main selected element from the latest Figma extraction Read get_figma_assets Get image and SVG assets from Figma Read get_figma_data When the nodeId cannot be obtained, obtain the layout information about the entire Figma file Read get_figma_dev_history Get the history of dev code extractions from the Figma plugin Read get_figma_dev_mode_code Get React + Tailwind code from Figma Read get_figma_page_structure Get detailed structure of specific pages in a Figma file with frame hierarchy Read get_figma_project_overview Get comprehensive overview of entire Figma file including structure, components, design system, and statistics Read get_figma_variable_definitions Get design variables and tokens from Figma Read get_JSON Get the raw JSON data from the latest Figma extraction with complete layout and styling information Read get_plugin_project_overview Get the project overview data directly from the Figma plugin scan. This provides the exact statistics shown in Read get_react_component Generate clean React component with TypeScript - works with plugin data or Figma API Read get_styled_component Generate styled-components React component - clean, modern styling Read get_tailwind_component Generate React component with Tailwind classes - smart design token conversion Read list_token_simulations List all active token change simulations and their status. Read map_app_flow Analyze app navigation flow and screen relationships based on naming patterns and structure Read rollback_token_change Rollback a previously applied token change to restore original values. Read simulate_token_change Simulate a design token change without actually applying it. Perfect for design reviews and impact planning. Read track_design_system_health Monitor design system health over time. Identifies token drift, unused tokens, inconsistent usage patterns.

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Can an AI agent delete data through the Sunnyside Figma MCP server? +

Yes. The Sunnyside Figma MCP server exposes 1 destructive tools including apply_token_change. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Sunnyside Figma MCP? +

The Sunnyside Figma MCP server has 2 write tools including generate_codegen_plugin, generate_migration_code. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Sunnyside Figma MCP.

How many tools does the Sunnyside Figma MCP server expose? +

31 tools across 4 categories: Destructive, Execute, Read, Write. 28 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Sunnyside Figma MCP? +

Register the Sunnyside Figma MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Sunnyside Figma MCP tool call.

Deterministic rules across all 31 Sunnyside Figma MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SUNNYSIDE FIGMA →

Free to start. No card required.

31 Sunnyside Figma MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Sunnyside Figma MCP

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL SUNNYSIDE FIGMA MCP

// ALL 31 SUNNYSIDE FIGMA MCP TOOLS

// RELATED SERVERS

// FAQ