Skip to main content
Glama
kenneives

design-token-bridge-mcp

extract_tokens_from_json

Parse W3C Design Tokens Community Group (DTCG) format JSON to extract universal design tokens for cross-platform translation.

Instructions

Parse W3C Design Tokens Community Group (DTCG) format JSON into universal tokens

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
jsonYesW3C DTCG format JSON string

Implementation Reference

  • Main handler function `extractTokensFromDTCG` that parses W3C DTCG format JSON and extracts design tokens. It flattens nested token structures, resolves aliases, and maps tokens to colors, typography, spacing, radii, elevation, and motion categories.
    export function extractTokensFromDTCG(jsonString: string): DesignTokens {
      let data: Record<string, unknown>;
      try {
        data = JSON.parse(jsonString);
      } catch {
        throw new Error("Invalid JSON: could not parse DTCG token file.");
      }
    
      // Flatten the nested token tree into a flat map
      const flatTokens = new Map<string, DTCGToken>();
      flattenTokens(data, [], flatTokens);
    
      if (flatTokens.size === 0) {
        throw new Error("No DTCG tokens found (no objects with $value).");
      }
    
      const tokens: DesignTokens = {};
      const colors: Record<string, ColorToken> = {};
      const typography: Record<string, TypographyToken> = {};
      const spacing: Record<string, number> = {};
      const radii: Record<string, number> = {};
      const elevation: Record<string, ElevationToken> = {};
      const motion: Record<string, MotionToken> = {};
    
      for (const [path, token] of flatTokens) {
        const resolvedValue = resolveAliases(token.$value, flatTokens);
        const type = token.$type ?? inferType(resolvedValue);
        const name = path.split(".").pop()!;
    
        switch (type) {
          case "color": {
            if (typeof resolvedValue === "string") {
              const hex = normalizeColor(resolvedValue);
              if (hex) {
                colors[name] = {
                  value: hex,
                  ...(token.$description ? { description: token.$description } : {}),
                };
              }
            }
            break;
          }
          case "dimension": {
            const px = parseDimension(resolvedValue);
            if (px !== null) {
              const lowerPath = path.toLowerCase();
              if (lowerPath.includes("radius") || lowerPath.includes("corner")) {
                radii[name] = px;
              } else {
                spacing[name] = px;
              }
            }
            break;
          }
          case "fontFamily":
          case "fontSize":
          case "fontWeight":
          case "typography": {
            if (type === "typography" && typeof resolvedValue === "object" && resolvedValue !== null) {
              const comp = resolvedValue as Record<string, unknown>;
              const typo: TypographyToken = {
                fontSize: parseDimension(comp.fontSize) ?? 16,
              };
              if (comp.fontFamily) typo.fontFamily = String(comp.fontFamily);
              if (comp.fontWeight) typo.fontWeight = Number(comp.fontWeight);
              if (comp.lineHeight) typo.lineHeight = parseDimension(comp.lineHeight) ?? undefined;
              if (comp.letterSpacing) typo.letterSpacing = parseDimension(comp.letterSpacing) ?? undefined;
              typography[name] = typo;
            } else if (type === "fontSize") {
              const px = parseDimension(resolvedValue);
              if (px !== null) typography[name] = { ...typography[name], fontSize: px };
            } else if (type === "fontWeight" && typeof resolvedValue === "number") {
              typography[name] = { ...typography[name], fontSize: typography[name]?.fontSize ?? 16, fontWeight: resolvedValue };
            } else if (type === "fontFamily" && typeof resolvedValue === "string") {
              typography[name] = { ...typography[name], fontSize: typography[name]?.fontSize ?? 16, fontFamily: resolvedValue };
            }
            break;
          }
          case "shadow": {
            const shadow = parseShadow(resolvedValue);
            if (shadow) elevation[name] = shadow;
            break;
          }
          case "duration": {
            const ms = parseDuration(resolvedValue);
            if (ms !== null) {
              motion[name] = { duration: ms, easing: "ease" };
            }
            break;
          }
          case "cubicBezier": {
            if (Array.isArray(resolvedValue) && resolvedValue.length === 4) {
              const [x1, y1, x2, y2] = resolvedValue;
              motion[name] = {
                duration: motion[name]?.duration ?? 300,
                easing: `cubic-bezier(${x1}, ${y1}, ${x2}, ${y2})`,
              };
            }
            break;
          }
        }
      }
    
      if (Object.keys(colors).length > 0) tokens.colors = colors;
      if (Object.keys(typography).length > 0) tokens.typography = typography;
      if (Object.keys(spacing).length > 0) tokens.spacing = spacing;
      if (Object.keys(radii).length > 0) tokens.radii = radii;
      if (Object.keys(elevation).length > 0) tokens.elevation = elevation;
      if (Object.keys(motion).length > 0) tokens.motion = motion;
    
      const hasContent = Object.values(tokens).some((v) => v !== undefined);
      if (!hasContent) {
        throw new Error("DTCG tokens found but none could be mapped to design tokens.");
      }
    
      return tokens;
    }
  • src/index.ts:96-113 (registration)
    Tool registration for 'extract_tokens_from_json' with schema defining a 'json' string input parameter. The handler calls extractTokensFromDTCG and returns formatted JSON output or error.
    server.registerTool(
      "extract_tokens_from_json",
      {
        description:
          "Parse W3C Design Tokens Community Group (DTCG) format JSON into universal tokens",
        inputSchema: {
          json: z.string().describe("W3C DTCG format JSON string"),
        },
      },
      async ({ json }) => {
        try {
          const tokens = extractTokensFromDTCG(json);
          return toolResult(JSON.stringify(tokens, null, 2));
        } catch (e) {
          return errorResult(e);
        }
      }
    );
  • DesignTokens interface defining the canonical output structure with optional colors, typography, spacing, radii, elevation, and motion token collections.
    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>;
    }
  • Helper function `flattenTokens` that recursively traverses the DTCG token tree and extracts tokens with $value fields into a flat map, handling inherited $type from parent groups.
    function flattenTokens(
      obj: Record<string, unknown>,
      path: string[],
      result: Map<string, DTCGToken>,
      inheritedType?: string
    ): void {
      // Check if this node has a group-level $type
      const groupType = typeof obj.$type === "string" ? obj.$type : inheritedType;
    
      for (const [key, value] of Object.entries(obj)) {
        if (key.startsWith("$")) continue; // Skip meta fields
    
        if (typeof value === "object" && value !== null) {
          const record = value as Record<string, unknown>;
          if ("$value" in record) {
            // This is a token
            const token: DTCGToken = {
              $value: record.$value,
              $type: (record.$type as string) ?? groupType,
              $description: record.$description as string | undefined,
            };
            result.set([...path, key].join("."), token);
          } else {
            // This is a group — recurse
            flattenTokens(record, [...path, key], result, groupType);
          }
        }
      }
    }
  • Helper function `resolveAliases` that resolves DTCG alias references (e.g., '{path.to.token}') by looking up and dereferencing token values from the flat token map.
    function resolveAliases(
      value: unknown,
      tokens: Map<string, DTCGToken>,
      depth = 0
    ): unknown {
      if (depth > 10) return value;
      if (typeof value === "string" && value.startsWith("{") && value.endsWith("}")) {
        const ref = value.slice(1, -1);
        const target = tokens.get(ref);
        if (target) {
          return resolveAliases(target.$value, tokens, depth + 1);
        }
      }
      return value;
    }
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It states the tool parses JSON into universal tokens but does not disclose behavioral traits such as error handling, performance characteristics, or what 'universal tokens' entail. This leaves significant gaps for a tool with no annotation coverage.

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 any wasted words. It is appropriately sized and front-loaded, making it easy to understand at a glance.

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?

Given the tool's complexity (parsing JSON into tokens), lack of annotations, and no output schema, the description is minimal. It states the purpose but does not cover behavioral aspects or output details, making it adequate but with clear gaps for informed tool selection.

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?

Schema description coverage is 100%, so the schema already documents the single parameter 'json' as a W3C DTCG format JSON string. The description adds no additional meaning beyond what the schema provides, such as format details or examples, resulting in the baseline score of 3.

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

Purpose5/5

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

The description clearly states the specific action ('Parse'), the input format ('W3C DTCG format JSON'), and the output ('universal tokens'), distinguishing it from siblings like extract_tokens_from_css or extract_tokens_from_figma_variables by specifying the input format.

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

Usage Guidelines4/5

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

The description implies usage when dealing with W3C DTCG format JSON, but does not explicitly state when to use this tool versus alternatives like extract_tokens_from_css or validate_contrast. It provides clear context but lacks explicit exclusions or named alternatives.

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