Figma-Context-MCP: Give Coding Agents Access to Figma Designs
Summary
Figma-Context-MCP is an MCP server that turns Figma file data into concise layout and styling context for AI coding agents. It is intended for developers who want agents such as Cursor to implement designs using design metadata rather than screenshots alone.
At a glance
- Language
- TypeScript
- License
- MIT
- Stars
- 15.9k
- Forks
- 1.3k
- Added to OSRepos
- January 14, 2026
- Last analyzed
- October 3, 2026
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Overview
Figma-Context-MCP connects AI coding tools to Figma through the Model Context Protocol. Given a Figma file, frame, or group link, it retrieves design information and condenses the Figma API response into layout and styling context for an agent.
It is useful when an agent needs more than a visual reference to implement a design. The project is designed with Cursor in mind, while its README describes use with other AI-powered coding tools that support MCP.
Key Features
- Fetches Figma data from links to files, frames, or groups.
- Translates Figma API responses into a more focused representation for coding agents.
- Provides layout and styling information to guide implementation.
- Uses MCP to connect Figma data to compatible AI coding tools.
- Can be launched through
npxwith a Figma access token. - Supports stdio configuration and documents environment variables for the API key and port.
Use Cases
- A frontend developer asks Cursor to implement a page or component from a Figma frame and wants the agent to use design metadata.
- A team prototyping a UI uses an MCP-compatible coding assistant to turn selected Figma layouts into code.
- A developer refining an existing interface provides a Figma group or frame so an agent can reference its layout and styling.
Project Facts
- Language: TypeScript
- License: MIT
- Stars: 15.9k
- Forks: 1.3k
- Topics: ai, cursor, figma, mcp, typescript
- Archived: No
Getting Started
Create a Figma personal access token, then configure an MCP client to run:
npx -y figma-developer-mcp --figma-api-key=YOUR-KEY --stdio
See the repository README and Framelink quickstart for client configuration details.
Considerations
- A Figma personal access token is required to retrieve design data.
- You need an AI client that supports MCP and can connect to this server.
- The project focuses on extracting and simplifying Figma data for coding agents; it is not described as a general-purpose design editor or a replacement for Figma.
Source repository
Open the original repository on GitHub.
25 counted GitHub visits
Related repositories
Similar repositories that may be relevant next.
OrcaReplay: Record and Replay AI Agent Runs
October 2, 2026
OrcaReplay records AI agent runs so developers can inspect what happened, replay interactions offline, and fork a run from a checkpoint onto another model. It is a TypeScript CLI for debugging and comparing agent behavior without modifying the agent.
openmake_llm: Coordinate AI Models, Agents, and Tools
October 1, 2026
OpenMake is a self-hosted AI workspace that coordinates chat models, agents, and tools in one place. It suits people who want multi-step AI workflows with local or open-weight models, while keeping infrastructure and model choices under their control.
zennotes: Manage Markdown Notes with Keyboard-First Tools
October 1, 2026
ZenNotes is a local-first Markdown notes app for people who prefer plain files, keyboard navigation, and Vim motions. It runs as an Electron desktop app or a self-hosted web app, with search, diagrams, CLI, and MCP integrations.
Kun: Local-First AI Agent Workspace
September 27, 2026
Kun is a local-first workspace for using AI agents across coding, writing, design, research, and automation. Its desktop GUI and terminal TUI share one runtime, keeping tasks and approvals connected.