genable-mcp
The genable-mcp server is a Figma design agent that lets you create, inspect, edit, and manage native Figma designs programmatically from any MCP client.
Design Generation
jsx— Create entire design trees using JSX-like markup (frames, text, icons, images, instances, vectors, etc.) with full auto-layout, styling, and gradient supportcreate_vector— Create vector nodes from SVG path data or polyline points (charts, icons, custom shapes)
Node Manipulation
edit— Batch update properties (size, opacity, radius, component props) on one or many nodesdelete_node— Delete a node and all its childrenmove_node— Relocate or rename a node without recreating itclone_node— Deep-copy a node with optional property overrides
Layout & Styling
set_text— Set text content on one or more text nodesset_fill— Set fill or background color (hex, gradient, variable token)set_stroke— Set border/stroke color, weight, and alignmentset_layout— Set auto-layout properties (direction, gap, padding, alignment, grid)
Inspection & Validation
inspect— Read node properties (layout, fills, strokes, typography, effects, variables, etc.)describe— Validate a design subtree for layout conflicts, overflow, missing properties, and structural issuesfind_nodes— Search nodes by name or type across the current pageget_selection— Retrieve the user's currently selected nodesget_screenshot— Capture a PNG screenshot of any node for visual verificationdiscover_props/replace_props— Find unique property values or bulk find-and-replace across a subtree (e.g., theming, token migration)
Variable & Token System
list_variables,create_collection,ensure_collection,create_variable,ensure_variable,set_variable_value,bind_variable,set_variable_mode,find_references— Full management of Figma variables, collections, and modes (e.g., Light/Dark theming)
Component System
create_component— Convert a frame or group into a Figma componentcombine_components— Combine multiple components into a variant setadd_component_prop/list_component_props— Manage TEXT, BOOLEAN, or INSTANCE_SWAP propertiescreate_instance— Create a live instance of an existing component
Knowledge & Guidance
skill— Load procedural workflow guidesstyle— Load visual style presets (color tokens, typography, mood)guideline— Load page-type design guidelines (landing pages, dashboards, forms, etc.)help— Load how-to documentation for tools, edge cases, and conventions
Page & File Navigation
switch_page— Navigate between pages or discover the page roster
Plugin Data
read_plugin_data/write_plugin_data— Read/write private or shared plugin metadata on nodes
Agent & Session Management
subtask— Delegate focused sub-tasks to typed child agents (create, audit, token operations)session_note— Persistent scratchpad for plans, decisions, failures, and learnings across turnsask_user— Present a structured multi-question form to clarify ambiguous design decisions
Provides tools for building and editing Figma designs, including JSX tree creation, variables/tokens, components, cross-page navigation, and visual verification.
Genable
Use your model. Keep the design.
Turn a detailed brief into native, editable Figma structure you can inspect and refine.
A design agent with a canvas to act on
Genable runs an agent loop against Figma's scene graph through typed design operations. It can plan a composition, build native structure, inspect the result, and continue refining it in context.
Plan the direction — Make audience, content, hierarchy, brand, mood, typography, density, and rhythm part of the brief.
Build native structure — Create and edit frames, Auto Layout, vectors, text, components, variables, and pages instead of returning one flat image.
Check the work — Inspect structure, read back writes, and use screenshots for visual verification when useful.
Keep refining — Continue the conversation with the current canvas in context; every generated layer remains available to edit in Figma.
Related MCP server: figma-unified-mcp
A visual direction, not a preset shell
Generic output often begins with a generic brief. Genable's design guidance pushes the model to treat composition, hierarchy, typography, density, rhythm, surfaces, and data presentation as connected decisions—not as a card grid with a new accent color.
No tool can guarantee taste. The model, source material, and judgment still matter. Genable keeps intent explicit and the result inspectable so refinement stays inside the workflow.
Choose the model that fits the brief
The Figma plugin supports provider presets and configurable compatible endpoints across three protocol families. It validates the provider before the first run and lets you switch models later without hard-coding this page to a specific model version.
Protocol | Typical connections |
OpenAI-compatible | OpenAI, OpenRouter, Moonshot, DeepSeek, DashScope, compatible endpoints |
Anthropic-compatible | Anthropic and compatible endpoints |
Gemini | Google AI Studio |
Provider credentials are stored in Figma client storage. Requests go to the endpoint you configure; some presets can use a relay when browser-network constraints require it. Provider billing and limits still apply.
One engine, two ways into Figma
Inside Figma: the plugin
Add a supported provider or compatible endpoint in Settings.
Describe the design in detail, then inspect and refine the native layers in conversation.
From an MCP client: genable-mcp
Use the model already configured in a STDIO MCP client. genable-mcp provides
a local, plugin-backed bridge for creating, editing, inspecting, and visually
verifying Figma designs; it does not require a second model API key inside
Genable.
{
"mcpServers": {
"genable": {
"command": "npx",
"args": ["-y", "genable-mcp"]
}
}
}Keep the Genable plugin running in Figma desktop, then ask your client to list the pages in the current file. See the current package docs for client-specific setup and the live tool schema.
Example briefs
Detail gives the model a real direction to work with. Adapt one of these to your product rather than treating it as a guaranteed output recipe:
“SaaS pricing page — three tiers, monthly/annual toggle, featured Pro plan, dark mode, and brand color bound to variables.”
“Analytics dashboard — sidebar, KPI grid with sparklines, compact holdings table, dark and light modes, and a calm editorial hierarchy.”
“Mobile onboarding — three screens with progress, illustration direction, named type scale, spacing rhythm, and one clear primary action.”
“Landing hero — audience and value proposition first, dual CTA, code preview, Inter typography, and an 8pt spacing scale.”
Sponsor
Genable is maintained by one developer. Sponsorship supports development time, real-model evaluation, and ongoing plugin and MCP improvements.
License
The material in this public repository and the genable-mcp package are
MIT-licensed. The Figma Community plugin is free; model-provider usage may be
billed separately.
Maintenance
Related MCP Servers
- AlicenseAqualityCmaintenanceFigma MCP server with full read/write access via plugin bridge — no API token, no rate limits. 58 tools for design automation: styles, variables, components, prototypes, and content.Last updated731,267MIT
- Alicense-qualityCmaintenanceA comprehensive MCP server that enables Claude to read, create, edit, and generate code from Figma designs. Supports design tokens, code generation to multiple frameworks, and accessibility checks.Last updated3MIT
- Alicense-qualityCmaintenanceRead-only Figma MCP server that enables design-to-code workflows by talking to the Figma REST API with a personal access token, for use with Claude Code and GitHub Copilot.Last updated3,175MIT
- Alicense-qualityDmaintenanceEnhanced Figma MCP Server that exposes prototype flow data — screen lists, prototype connections, and full flow maps — via the Figma REST API. Designed as a replacement for the official Figma MCP server, adding prototype interaction layer so Claude Code can understand entire user flows from a single Figma URL.Last updated151MIT
Related MCP Connectors
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
Real-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/musepy/genable'
If you have feedback or need assistance with the MCP directory API, please join our Discord server