The F2C MCP Server acts as a Model Context Protocol server for Figma, enabling seamless integration between designs and coding tools. It can:
Convert Figma design nodes into high-fidelity code in multiple formats (HTML/CSS, React with CSS Modules, or React with Tailwind CSS)
Provide Figma design context to AI coding tools like Cursor
Retrieve detailed file information with options for depth, version, geometry, branch data, and plugin data
Get images of specified Figma nodes in various formats (jpg, png, svg, pdf) with scale options
Fetch all image resources used as fills within a Figma file
Access metadata information for Figma files
Support Figma file URLs with fileKey and nodeId parameters
Converts Figma design elements to CSS code, allowing for high-fidelity representation of designs in web development
Enables AI coding assistants to access Figma design data, convert Figma design nodes to high-fidelity HTML/CSS markup, and provide Figma design context to AI coding tools
Links to the project repository for access to the source code and related resources
Provides package distribution through npm, with version tracking and dependency management
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@f2c-mcp-server convert this Figma design to React code"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Due to Figma REST API rate limits, if you are affected, please switch to @f2c/mcp-plugin for normal operation.
English | 简体中文
A Model Context Protocol server for Figma Design to Code using F2C.
🎨 Pixel-Perfect HTML/CSS：F2C converts Figma designs to pixel-perfect HTML/CSS with precision.
⚛️ Multi-Framework Support：F2C generates React, CSS Modules, and Tailwind CSS code for fast development.
🧠 Figma Design Context：F2C integrates design context, ensuring compatibility with AI tools like Cursor.
🔗 Figma File URL Parsing：F2C converts design nodes via Figma URLs, streamlining workflows.
🖼️ Remote Image Localization：F2C automates downloading Figma images to local assets for efficiency.
Related MCP server: mcp-figma
Configure the Server in an MCP-supported IDE (e.g., Cursor, Trae).
recommended to use Comate AI IDE
Open your chat in IDE (e.g. agent mode in Cursor).
Paste a link to a Figma Node (Right-click any node in the Figma Layer panel to copy it).
Enter your requirements in the chat, such as fetching node data, downloading images, converting to code, etc.
See Configuration and Development
The logging tools integrated in this project are used solely for basic usage statistics and error log reporting. No sensitive information or user data is collected. All reported data is used exclusively to improve product quality and user experience.
See FAQ
Thanks to:
Framelink Figma MCP Server Give Cursor and other AI-powered coding tools access to your Figma files with this Model Context Protocol server.
Cursor Talk to Figma MCP Allowing Cursor to communicate with Figma for reading designs and modifying them programmatically.
Figma MCP Server This server provides tools for viewing, commenting, and analyzing Figma designs directly through the ModelContextProtocol.
Get detailed information about a Figma file
Inputs: fileKey (required), ids (required), branch_data, depth, +4 more.
Get metadata information for a Figma file
Inputs: fileKey (required), personalToken.
Get all image resources in the specified Figma file
Inputs: fileKey (required), personalToken.
Get images of Figma nodes
Inputs: fileKey (required), ids (required), format, personalToken, +5 more.
Convert Figma designs into code. This tool extracts specified Figma nodes and transforms them into HTML, React with CSS Modules, or React with Tailwind CSS, facilitating automated design-to-code conversion.
Inputs: fileKey (required), ids (required), format, personalToken.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 5 tools
The tools have some overlap in purpose, particularly between 'figma_get_file_data' and 'figma_get_file_meta', which could cause confusion about which to use for general file information. However, descriptions help clarify distinctions, such as 'figma_get_image_fills' for image resources versus 'figma_get_images' for node images, and 'figma_to_code' has a unique conversion function.
All tool names follow a consistent 'figma_' prefix with snake_case and descriptive verb_noun patterns, such as 'get_file_data' and 'to_code'. There are no deviations in naming conventions, making the set predictable and easy to understand.
With 5 tools, the count is reasonable for a Figma-to-code server, covering data retrieval, image handling, and conversion. It's slightly under the ideal range for comprehensive coverage but well-scoped for core functionalities without being overwhelming.
The tool set covers key operations like retrieving file data, metadata, images, and converting to code, but there are notable gaps, such as missing update or delete operations for Figma files, and no tools for managing design components or handling user interactions, which limits full lifecycle coverage in the design-to-code domain.
A simple MCP server built with FastMCP and python