Skip to main content
Glama
Adobe XD MCP

Adobe XD MCP

by srayan-uxd

xd_get_design_system

Extract the design system used in an .xd file—colors, typography, radii, strokes, and shadows—and export it as JSON, CSS variables, Tailwind theme, or Figma variables.

Instructions

Extract the design system actually used in the file: color palette (ranked, with fill/text/stroke usage), typography styles and size scale, corner radii, stroke widths and shadows. Output as json, css (custom properties), tailwind (theme.extend) or figma-variables (variable collections, text styles named by role and effect styles, ready to create in Figma).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "file": "<file>"
    },
    "name": "xd_get_design_system"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYesAbsolute path to a .xd file
formatNojson

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.0
    • changedInput schema / properties / format / enum
      Previous value: -[
      -  "json",
      -  "css",
      -  "tailwind"
      -]New value: +[
      +  "json",
      +  "css",
      +  "tailwind",
      +  "figma-variables"
      +]
  2. First observedv0.2.0

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full burden, and it does substantial work: it discloses that colors are ranked and annotated with fill/text/stroke usage, that the output is a computed analysis of what is "actually used" rather than a raw dump, and what each of the four output modes produces. It stops short of stating read-only safety explicitly, whether the whole file or a single artboard is scanned, or what happens when the file has no defined styles.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the extraction scope and followed by the output-format menu; every clause names a concrete artifact rather than filler. The parenthetical lists are dense but each item adds real information, so nothing meaningful could be cut without losing specificity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read tool with no output schema, the description does the important work of describing the return shape across four formats. However, it leaves the agent guessing on scope (entire document vs. artboards), on the read-only/non-destructive nature, and most importantly on how this differs from the closely named xd_get_design_tokens sibling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 50% schema coverage, the description compensates for the undocumented format parameter by explaining all four enum values concretely: css as custom properties, tailwind as theme.extend, and figma-variables as variable collections plus text styles named by role and effect styles ready to create in Figma. The file parameter is left entirely to the schema, which already documents it as an absolute path to a .xd file.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: "Extract the design system actually used in the file," then enumerates exactly what is captured (colors with usage breakdown, typography scale, radii, stroke widths, shadows). It is far more concrete than the name alone, but it never differentiates itself from the sibling xd_get_design_tokens, which an agent could easily mistake for the same operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: the tool is for pulling a design system out of an .xd file, and the format list hints at downstream destinations (CSS, Tailwind, Figma variables). There is no explicit when-to-use versus xd_get_design_tokens, xd_font_report, or xd_get_shared_assets, and no stated prerequisites such as whether the file must be open or previously inspected.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.