"Figma" matching MCP servers:

Enables listing top-level frames in a Figma file and fetching a selected frame's rendered PNG, node JSON, and image-fill map into a local output directory.

Pull a Figma frame once, then let Claude Code, Codex or any MCP agent read it offline with no rate limits. Six read-only tools serve the normalized node tree, design tokens and locally built SVG icons from a vault you can commit, so teammates need no Figma token.

Enhanced 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.

Exports frames from Figma and uploads them to Google Drive, with automated folder creation.

Local MCP server exposing Figma REST API tools to AI agents, enabling file reads, comments, variables, and other resource operations. Works with personal access tokens and integrates with Claude, Cursor, Codex, and more.

Bridges AI clients to Figma Desktop via Plugin API and WebSocket, enabling real-time design manipulation without rate limits.

Figma MCP with full API functionality

Enables stdio MCP clients such as Cursor and Claude Code to read and modify the currently open Figma Desktop file, export selected nodes as local PNG/SVG files, and create or edit basic canvas nodes using precise layout data for pixel-level reconstruction.

基于MCP协议的工具，用于从Figma获取设计节点数据并转换为结构化DSL，辅助生成Vue 3 / React / HTML组件代码。

Read-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.

Enables AI agents to inspect Figma design files by fetching file summaries, page structures, specific nodes, and rendered image previews, along with signed-in user details and file comments. It lets agents review design feedback and explore frames, components, and layers without downloading full node trees.

Enables agents to compare a live web page against a Figma frame and receive a bounded JSON verdict of design deviations, without sending screenshots or mockups through the model context.

Enables AI agents to create, modify, and manage Figma designs through natural language commands via a specialized MCP server and plugin bridge. It supports a wide range of operations including element creation, property modification, component management, and accessibility checks.

An MCP server that bridges Claude Code to Figma, enabling AI-driven design creation, modification, and export via semantic tools and WebSocket communication.

Enables AI assistants to access locally installed fonts and control Figma text through a local bridge, including listing, auditing, replacing, and setting fonts on text nodes.

Enables AI agents to read and draw on Figma canvas safely, with built-in safeguards for layout, overlays, and verification.

Provides read-only Figma design data to AI agents via MCP, supporting local .fig files and browser-based figma.com access without plugins or API tokens.

An MCP server that lets AI agents drive FigJam boards through a local Figma plugin, bypassing API rate limits with 19 tools for reading, writing, and editing FigJam content.

Bridge Figma designs to any platform with structured specs for Unity, React, Flutter, SwiftUI, and more, including layout audit, design tokens, and accessibility checks.

Read, create, and modify Figma designs programmatically via MCP, empowering AI to execute Figma changes safer, cleaner, and faster.