figma-vault

English · Русский

Pull a Figma frame once. Then Claude Code, Codex or any MCP agent reads it as often as it likes: offline, with no Figma token and no rate limits.

• Batch Figma requests once, then zero requests however many times the agent looks. Screens from one file share the structure read and image render batches.
• Icons cost nothing. A real screen had 141 icons, and they took no extra requests.
• Commit the vault and the team needs no Figma access. No licence, no token.

Try it in 30 seconds. You don't need a Figma token for this:

npm i -g figma-vault
figma-vault init && figma-vault demo && figma-vault check

How it works: the pull normalizes the frame and writes it to disk. The agent then reads it over MCP.

one developer:      figma-vault add <link>  →  vault  →  git commit
the rest of the team:  the agent reads it over MCP, no Figma token needed

The problem

Figma's MCP server and REST API are rate-limited, and on some seats the limit is tiny. While building a UI, an agent goes back to the design all the time to check a margin, a colour or a font size. That can mean dozens of calls in one session. You hit the limit fast and the work stops.

With figma-vault, the number of Figma calls doesn't depend on what the agent does. Each design costs a fixed number of calls, spent once when you pull it.

There's a side effect: the design becomes a file in your repository. A developer without access to the Figma file (no licence, no permissions, no token) still gets the whole design.

How it compares

Other projects work on the same problem. The Framelink Exporter plugin exports a design to a zip for offline use, and there are caching forks of Framelink's Figma MCP. figma-vault takes a different approach:

• The vault is meant to be committed. One person pulls a design and the whole team reads it from git. Nobody else needs Figma access.
• Icons cost zero requests. Vector paths come with the node tree, and the SVGs are built locally. Rendering them through Figma would eat the image-render limit.
• The format is fixed and validated. doc.json follows a written contract, and a strict validator checks every file.

Install

Requires Node.js 22+.

npm i -g figma-vault

Option 1. Per project

figma-vault init

This creates .figma-vault/, registers the server in the project's .mcp.json (other entries are left alone), adds .env to .gitignore and installs a /figma slash command for Claude Code.

Use --no-command to skip the /figma command, so the agent gets only the read-only vault_* tools.

Option 2. Nothing in the repository

figma-vault init --global

The vault lives in ~/.figma-vault/ and the server is registered in the agent's user config. The project repository never learns the tool exists. Use this when you can't add config or dependencies to the project.

Usage

figma-vault add "https://figma.com/design/KEY/Project?node-id=127-4532"
# Export several selections together; links from the same file share requests:
figma-vault add "<frame link 1>" "<frame link 2>"
# Keep the node trees if image rendering is unavailable:
figma-vault add "<frame link 1>" "<frame link 2>" --no-assets
# A SECTION/CANVAS link can expand into its frames (up to 20 by default):
figma-vault add "<section link>" --expand --max-screens 20

To get the link, right-click a frame in Figma and choose Copy link to selection.

figma-vault limits "<frame link 1>" "<frame link 2>" # probe access before pulling
figma-vault list              # what has been pulled so far
figma-vault check             # verify the whole chain works
figma-vault demo              # add a demo design, no token needed

CLI output, errors and the MCP tool descriptions are in English by default; the /figma command it installs is in English too. README.ru.md is a translation of the documentation only.

After init, Claude Code has one command:

/figma <frame link> [more frame links...]

It pulls the design, reads it over MCP and builds the UI following the project's conventions.

What a pull costs in Figma requests

REST API limits depend on the token, plan and seat type. Both node reads and image renders are Tier 1 endpoints. figma-vault limits "<link>" [more links...] spends one shallow node read plus up to ceil(S/40) screen render requests per file. It skips rendering SECTION and CANVAS selections as whole images; their child screens are not probed. A successful probe cannot guarantee the full pull: asset renders can require additional requests.

For a file with S selected screens and R unique raster assets, when each screen has fewer than 40 raster assets, a successful pull typically uses:

For example, two screens in one file with three unique raster assets take one node read and one image render if the five IDs fit in a batch. At 40 or more raster assets on one screen, screenshots are rendered separately. --expand first probes containers with depth=1, adding at least one node request per file. SVG fallback renders, failed requests and retries can add calls. On a real 332-node design, 141 icons needed no render calls. After the pull, the agent never calls Figma again.

Check the result against the design

figma-vault verify compares the page the agent built with the design. The package ships no browser: the snapshot is taken with whatever the project already uses (Playwright, DevTools, the agent's browser tool).

1. Mark the root element of the page with data-figma-node-id="<root node id>", and the main blocks with the ids of their nodes.
2. figma-vault verify <docId> --snippet prints a script. Run it on the page and save what it returns to a file.
3. figma-vault verify <docId> --snapshot <file> checks it:
   • texts: every visible text of the design must be on the page;
   • geometry: each marked block must match the design's position and size, within 2 px by default (--tolerance).

The result is PASS (exit code 0), FAIL (1, with a list of what is off) or INCOMPLETE (2, when nothing is marked and geometry can't be checked). The /figma command runs this step itself when the project has a browser.

Try it without a Figma token

You only need a token to pull new designs. Reading works without one, which is the normal setup for everyone except the person who pulls. So you can test the whole install without creating a token:

figma-vault init && figma-vault demo && figma-vault check

check starts the real MCP server as a child process and talks to it over the protocol. It exits with code 1 when something is actually broken, so you can use it in CI.

Token

In Figma, go to Settings → Security → Personal access tokens → Generate new token. The token needs only one scope: File content → Read-only.

Put it in a .env file in the directory you run the CLI from, as a line FIGMA_TOKEN=figd_..., or set it as an environment variable. If both are set, the environment variable wins.

What the agent gets

The MCP server exposes six read-only tools:

The tree is normalized:

• auto-layout becomes mode: row|column with gap and padding;
• coordinates are relative to the parent;
• styles, gradients and text come in one predictable shape, including differently coloured fragments inside one text (text.runs);
• nodes hidden in Figma are kept with hidden: true. By default the agent doesn't get them, but a parent reports how many it has (hiddenOmitted). Pass includeHidden: true when building a reusable component whose optional slots are switched off on this screen.

The raw Figma response is saved next to it in raw.json for debugging.

On a real design, normalization shrinks the tree about 7 times:

raw.json   1.9 MB   raw Figma response
doc.json   256 KB   what the agent reads

This saves more than disk space. An agent that reads 256 KB instead of 2 MB rebuilds the UI noticeably more accurately.

Vault layout

<vault>/
  index.json                 list of designs
  <docId>/
    doc.json                 normalized tree, the main artifact
    raw.json                 raw Figma response
    screenshot.png           render of the whole frame
    assets/                  icons and images