Figma Local Context (offline .fig reader)

    1

    Reads local Figma .fig and .make files offline, with no Figma API or token, to inspect nodes, extract layout and style details, and export SVG or PNG.

    Free

    2 usesSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Figma Local Context (offline .fig reader)

    Example session with this skill installed

    Use figma-local-context-mcp to inspect ./designs/login-screen.fig. Find the 'Login Button' frame, get its design tokens, and export it as an SVG to ./src/assets/login-btn.svg.

    • Read your context and instructions
    • Compiled the figma local context
    • Generated the design tokens stylesheet

    I have inspected the Figma file and extracted the requested details for the 'Login Button'.

    Figma Node Inspection & Export

    ActionResultDetails
    Node Found2625:12945Name: "Login Button", Type: "FRAME"
    Dimensions240 x 48X: 120, Y: 450
    Export StatusSuccessSaved to ./src/assets/login-btn.svg
    Rendererlocal-svgScale: 2x

    Extracted Design Tokens

    • Colors: #3B82F6 (Primary Blue, 1 use), #FFFFFF (Text, 1 use)
    • Shadows: 0px 4px 6px rgba(0, 0, 0, 0.1)
    • Stroke: 1px solid #2563EB

    CSS Implementation Hint

    /* Login Button Context */
    .login-button {
      width: 240px;
      height: 48px;
      background: #3B82F6;
      border: 1px solid #2563EB;
      border-radius: 8px;
      box-shadow: 0px 4px 6px 0px rgba(0, 0, 0, 0.10);
      display: flex;
      align-items: center;
      justify-content: center;
    }
    

    Next steps

    1. Verify the exported SVG in your src/assets/ folder.
    2. Use the provided CSS snippet to style your button component.
    3. Run get_design_tokens on the parent frame to check for shared color variables.

    figma-local-context-offline-fig-reader-tokens.css

    CSS · design tokens

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Developers building UI often waste time manually copying hex codes and dimensions from Figma, or waiting for design handoffs. This skill enables AI agents to read local .fig and .make files directly through a Model Context Protocol (MCP) server, bypassing the Figma API and authentication requirements.

    What it does

    • Inspect local files to retrieve node counts, layer hierarchies, and element summaries from .fig and Figma Make packages.
    • Extract design tokens such as solid colors, linear gradients, drop shadows, and stroke widths directly from the file content.
    • Generate implementation hints including CSS values, layout boxes, and export suggestions for frames and vector nodes.
    • Export assets as SVG or PNG files directly into project directories without needing the Figma desktop app open.
    • Analyze Figma Make files to read source code components, AI chat summaries, and package metadata.

    How it works

    1. Use inspect_fig_file to get an overview of the document structure and node types.
    2. Search for specific frames or components using list_fig_nodes by name or ID.
    3. Call get_design_context or get_code_context to pull dimensions, CSS properties, and tokens for implementation.
    4. Run export_assets to save icons and illustrations to a local src/assets/ directory.

    Frameworks & tools

    Built for use with Node.js 20.20.0+ and any MCP-compatible agent like Claude Code or Cursor. It uses @resvg/resvg-js for local asset rendering.

    Why this beats prompting it yourself

    Standard agents cannot parse binary .fig files and usually require manual screenshots or API access. This skill provides direct, offline access to the underlying design data, ensuring your agent writes code based on exact dimensions and colors rather than visual guesses.

    Use cases

    • Generating React or Tailwind components that match a local design file precisely.
    • Automating the extraction of design tokens into a theme.ts or variables.scss file.
    • Batch exporting icons from a design system file into a web project.
    • Auditing local Figma files for consistency in stroke weights and color usage.

    Known limitations

    Does not support Figma typography data like font families or line heights. Rendering is a local approximation and may not match Figma pixel-for-pixel. Limited to read-only operations.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Frontend & Web Apps.

    Read-only. No typography or text content extraction. PNG/SVG exports are local approximations. Requires local .fig files; no cloud-only support. No Figma variables or styles registry access.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 27 days ago

    • Free with an Agensi account

    Software
    Node.jsGit

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Listed27 days ago

    What's inside

    Frequently Asked Questions

    This skill uses a Model Context Protocol (MCP) server to parse local .fig and .make files directly, meaning you don't need a Figma account, API tokens, or an active internet connection to extract design data.

    It is compatible with any MCP-enabled AI environment, including Claude Code and Cursor, provided you have Node.js 20.20.0 or higher installed on your machine.

    While the tool provides highly accurate dimensions, CSS hints, and color tokens, it currently does not support typography data like font families or line heights due to local rendering limitations.

    Yes, the skill includes an 'export_assets' function that uses a local rendering engine to save frames and vector nodes as SVG or PNG files directly into your project folders.

    Upon purchase, you receive the full MCP server package, including the necessary binaries and configuration instructions to connect it to your preferred AI agent.

    New in Frontend & Web Apps

    Free