@adobe/design-data-agent-mcp
Enables teams to query and analyze design system data programmatically within Claude, reducing manual data extraction and accelerating design-to-engineering …
MCP server and Claude Code skill for Adobe's Spectrum Design Data. Read tools (primer, resolve_token, query_tokens, describe_component) run in-process via WebAssembly with no CLI binary required; one authoring tool still calls the @adobe/design-data CLI. Lets agents query design tokens and component schemas from MCP clients like Claude Code and Cursor.
- Ask Claude to analyze design system usage patterns across your product applications.
- Generate reports on component adoption rates and performance metrics from design data.
- Find inconsistencies in design token implementation across your codebase quickly.
Enables teams to query and analyze design system data programmatically within Claude, reducing manual data extraction and accelerating design-to-engineering handoff cycles.
Design systems teams and engineering leads standardizing design token management and automating design asset workflows.
https://github.com/adobe/spectrum-design-data/tree/main/tool...
By GitHub Actions
How to Get It
npx -y @adobe/design-data-agent-mcp
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Analyze design system usage patterns across my product applications
Trust Signals Auto-scanned
Data & Access
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 141 GitHub stars; contributors unknown; last commit 2d ago; license Apache-2.0.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 141 GitHub stars; contributors unknown; last commit 2d ago; license Apache-2.0.