Skip to main content
Glama
kenneives

design-token-bridge-mcp

extract_tokens_from_tailwind

Extract design tokens from Tailwind CSS configuration files to create universal theme values for cross-platform design systems.

Instructions

Parse a Tailwind config and extract theme values into universal design tokens

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
configYesThe contents of a tailwind.config.js or tailwind.config.ts file

Implementation Reference

  • The main handler function `extractTokensFromTailwind` that parses a Tailwind config file's text content and extracts design tokens for colors, typography, spacing, border radii, and elevation/shadows. It uses regex-based static analysis (no eval) to safely extract the theme object from both CJS and ESM config formats.
    export function extractTokensFromTailwind(configContent: string): DesignTokens {
      const themeObj = extractThemeObject(configContent);
      if (!themeObj) {
        throw new Error(
          "Could not extract theme from Tailwind config. Ensure the config exports a theme or theme.extend object."
        );
      }
    
      const tokens: DesignTokens = {};
    
      // Colors
      const colors = themeObj.extend?.colors ?? themeObj.colors;
      if (colors && typeof colors === "object") {
        tokens.colors = extractColors(colors);
      }
    
      // Typography (fontSize)
      const fontSize = themeObj.extend?.fontSize ?? themeObj.fontSize;
      if (fontSize && typeof fontSize === "object") {
        tokens.typography = extractTypography(fontSize);
      }
    
      // Font family — merge into typography if present
      const fontFamily = themeObj.extend?.fontFamily ?? themeObj.fontFamily;
      if (fontFamily && typeof fontFamily === "object") {
        if (!tokens.typography) tokens.typography = {};
        for (const [name, value] of Object.entries(fontFamily)) {
          const family = Array.isArray(value) ? value[0] : String(value);
          // Create or update a typography entry for this font family
          tokens.typography[`font-${name}`] = {
            fontFamily: family,
            fontSize: 16, // default base size
          };
        }
      }
    
      // Spacing
      const spacing = themeObj.extend?.spacing ?? themeObj.spacing;
      if (spacing && typeof spacing === "object") {
        tokens.spacing = extractNumericMap(spacing);
      }
    
      // Border radius -> radii
      const borderRadius = themeObj.extend?.borderRadius ?? themeObj.borderRadius;
      if (borderRadius && typeof borderRadius === "object") {
        tokens.radii = extractNumericMap(borderRadius);
      }
    
      // Box shadow -> elevation
      const boxShadow = themeObj.extend?.boxShadow ?? themeObj.boxShadow;
      if (boxShadow && typeof boxShadow === "object") {
        tokens.elevation = extractElevation(boxShadow);
      }
    
      // Ensure we have at least one category
      const hasContent = Object.values(tokens).some((v) => v !== undefined);
      if (!hasContent) {
        throw new Error("Tailwind config theme contained no extractable token values.");
      }
    
      return tokens;
    }
  • src/index.ts:33-54 (registration)
    Registration of the `extract_tokens_from_tailwind` tool with the MCP server. Defines the input schema (config: string) and the async handler that calls `extractTokensFromTailwind` and returns JSON-formatted tokens.
    server.registerTool(
      "extract_tokens_from_tailwind",
      {
        description:
          "Parse a Tailwind config and extract theme values into universal design tokens",
        inputSchema: {
          config: z
            .string()
            .describe(
              "The contents of a tailwind.config.js or tailwind.config.ts file"
            ),
        },
      },
      async ({ config }) => {
        try {
          const tokens = extractTokensFromTailwind(config);
          return toolResult(JSON.stringify(tokens, null, 2));
        } catch (e) {
          return errorResult(e);
        }
      }
    );
  • The `DesignTokens` interface defining the canonical intermediate format that all extractors produce. Includes optional categories for colors, typography, spacing, radii, elevation, and motion.
    export interface DesignTokens {
      colors?: Record<string, ColorToken>;
      typography?: Record<string, TypographyToken>;
      spacing?: Record<string, number>; // px values
      radii?: Record<string, number>; // px values
      elevation?: Record<string, ElevationToken>;
      motion?: Record<string, MotionToken>;
    }
  • Type definitions for `ColorToken` and `TypographyToken` interfaces used by the extracted design tokens.
    export interface ColorToken {
      value: string; // hex color, e.g. "#6750A4"
      description?: string;
      category?:
        | "primary"
        | "secondary"
        | "tertiary"
        | "neutral"
        | "error"
        | "surface"
        | "background"
        | "custom";
    }
    
    export interface TypographyToken {
      fontFamily?: string;
      fontSize: number; // px
      lineHeight?: number; // px
      fontWeight?: number; // 100-900
      letterSpacing?: number; // px
    }
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool parses and extracts values, implying a read-only operation, but lacks details on error handling, output format, performance considerations, or any side effects. This leaves significant gaps in understanding how the tool behaves beyond its basic function.

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

Conciseness5/5

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

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is front-loaded and every part contributes to understanding the action and resource, making it highly concise and well-structured.

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

Completeness2/5

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

Given the complexity of parsing and extracting design tokens, the lack of annotations, and no output schema, the description is insufficient. It doesn't explain what 'universal design tokens' entail, how results are returned, or any limitations, leaving the agent with incomplete context for effective use.

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

Parameters3/5

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

The schema description coverage is 100%, with the single parameter 'config' fully documented in the schema as 'The contents of a tailwind.config.js or tailwind.config.ts file'. The description adds no additional meaning beyond this, such as format specifics or examples, so it meets the baseline for high schema coverage without compensating further.

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?

The description clearly states the action ('parse', 'extract') and resource ('Tailwind config', 'theme values', 'universal design tokens'), making the purpose evident. It distinguishes from some siblings like 'extract_tokens_from_css' by specifying the source as a Tailwind config, though it doesn't explicitly differentiate from all siblings like 'extract_tokens_from_figma_variables'.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives. The description mentions parsing a Tailwind config, but it doesn't specify scenarios, prerequisites, or exclusions, such as when to choose this over 'extract_tokens_from_css' or 'generate_tailwind_config'.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/kenneives/design-token-bridge-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server