---
title: "Supernova.io — AI capabilities"
description: "Supernova has repositioned as “the agentic design system platform” (verbatim from https://www.supernova.io/llms.txt). Two consumption surfaces exist: (1) Supernova…"
url: "https://state-of-ai-in-design-systems.netlify.app/platforms/supernova.md"
canonical: "https://state-of-ai-in-design-systems.netlify.app/platforms#supernova"
type: "platform-record"
json: "https://state-of-ai-in-design-systems.netlify.app/platforms/supernova.json"
id: "supernova"
capability_count: 7
design_systems_with_integration_records: 0
data_collected: "2026-07-26/27"
generated: "2026-07-28T06:01:02Z"
report: "State of AI in Design Systems — July 2026"
author: "Kaelig Deloumeau-Prigent"
license: "CC-BY-4.0"
citation: "Deloumeau-Prigent, K. (2026). State of AI in Design Systems. https://state-of-ai-in-design-systems.netlify.app/platforms/supernova.md"
---

> Snapshot of 2026-07-27. Every claim below links to the source URL it was taken from. Check the source before citing.

# Supernova.io — AI capabilities

7 capabilities recorded. 0 of the 19 design systems in this study carry an integration record for this platform.

- This record as JSON: https://state-of-ai-in-design-systems.netlify.app/platforms/supernova.json
- Platforms view: https://state-of-ai-in-design-systems.netlify.app/platforms.md

## Summary

Supernova has repositioned as “the agentic design system platform” (verbatim from https://www.supernova.io/llms.txt). Two consumption surfaces exist: (1) Supernova Relay, the official remote MCP server at https://mcp.supernova.io/mcp/ds/{ID} (OAuth, 14 read-only tools spanning tokens, DS components, code components, Figma components, Storybook stories, assets and docs-as-Markdown; explicitly read-only, “can’t make changes to data inside Supernova”); and (2) AI Context Management (shipped 22 Jun 2026), which lets a DS team define per-team scoped contexts: design tokens, component APIs, component patterns, usage data, rules, docs, plus “knowledge files, rules, and custom skills”, and publish each as its own context-scoped MCP endpoint, with a feedback loop capturing both engineer flags and automatic agent-interaction captures. On the builder side: Write with AI / documentation AI agents, and exporters (Supernova exporter store) that ship skills and knowledge files into repos. Marketing llms.txt exists at supernova.io/llms.txt and a human-readable /for-ai index page. PRICING/AVAILABILITY (from supernova.io/pricing): Free = 5 MCP consumers, 2 AI contexts, 2,400 automation credits/mo; Pro ($35/full seat/mo) = up to 50 MCP consumers, 10 AI contexts, 3,000 credits/seat/mo; Enterprise = custom MCP consumers, unlimited AI contexts, 5,000 credits/seat/mo. “Unlimited MCP lookups/month” on all tiers; dynamic filtering is Pro/Enterprise only. GAPS: no public Code Connect-style Figma↔code mapping file format found; no published per-styleguide llms.txt generation for customer docs sites (unlike zeroheight/Knapsack); the named AI agents (PM/Release note/Documentation/Architect) appear in blog/marketing copy but it was not possible to fetch a canonical docs page describing them, so treat as unverified. No named customer publicly documented as using the MCP.

## Capabilities (7)

### Supernova Relay — official remote MCP server (per design system)

Audience: consumers

Official, OAuth-authenticated remote MCP server scoped to a design system ID, optionally to a dataset via ?datasetId=. Documentation is converted to clean Markdown and token references are fully resolved across nested aliases before being handed to the model. Read-only by design. Supports Claude Desktop, Cursor, VS Code.

Link: https://learn.supernova.io/latest/design-systems/features/mcp-for-design-system-LIHAMhjr-LIHAMhjr

```json
{
  "mcpServers": {
    "supernova": {
      "url": "https://mcp.supernova.io/mcp/ds/{ID}",
      "type": "http"
    }
  }
}
```

Source: https://learn.supernova.io/latest/design-systems/features/mcp-for-design-system-LIHAMhjr-LIHAMhjr

### 14 MCP tools: tokens, components, code components, Figma, Storybook, docs

Audience: consumers

Verbatim tool inventory: get_asset_detail, get_asset_list, get_code_component_detail, get_code_component_list, get_design_system_component_detail, get_design_system_component_list, get_documentation_page_content, get_documentation_page_list, get_figma_component_detail, get_figma_component_list, get_me, get_storybook_story_detail, get_token_list. Notable descriptions: get_token_list “Pulls the full list of design tokens, including values, references, and groupings (e.g., colors, spacing)”; get_documentation_page_content “Grabs the content of a specific documentation page, formatted nicely (e.g., as markdown)”; get_figma_component_detail “Retrieves full details on a Figma component, including its structure, variants, and export options.” The get_code_component_* pair plus get_figma_component_* is Supernova’s de-facto Code-Connect equivalent: design-side and code-side component records live in the same MCP surface.

Link: https://learn.supernova.io/latest/design-systems/features/mcp-for-design-system-LIHAMhjr-LIHAMhjr

### AI Context Management — per-team, context-scoped MCP endpoints (shipped 22 Jun 2026)

Audience: both

The strongest coercion mechanism in Supernova: rather than one firehose MCP, the DS team curates a context (tokens, component APIs, patterns, usage data, rules, docs) per team/workflow/agent type and publishes it as its own MCP endpoint, reducing token usage and narrowing what the agent can even see. Explicitly framed as eliminating “hallucinated component names or incorrect prop signatures”. Includes a feedback loop: engineers flag manually, agent interactions are captured automatically, and Supernova returns “an actionable suggestion and a clear path to fix it”.

Link: https://www.supernova.io/blog/we-just-shipped-ai-context-management

```text
AI context management lets you define exactly what each team's agents need to know (design tokens, component APIs, component patterns, usage data, rules, and docs) and publish it as a focused, context-scoped MCP endpoint. Every coding or design tool your team uses can be plugged in directly.

[...]

Publish as a context-scoped MCP endpoint
Each context publishes as its own MCP endpoint. Cursor, Copilot, Claude Code, Codex, or any MCP-compatible tool can plug in directly. No custom integrations, no manual syncing.

Give agents access to real component data
Agents get access to real component APIs: props, import paths, valid compositions, and usage patterns. Engineers get accurate answers without leaving their flow. No more hallucinated component names or incorrect prop signatures.

Manage and distribute skills
Beyond raw data, you can build, curate, and refine the capabilities your agents bring to every interaction: knowledge files, rules, and custom skills. Ship them through predefined or custom exporters when ready.

Update once, and every agent gets it instantly
When your design system changes, your context updates automatically. Every connected agent is working from current information without anyone having to manually push updates.
```

Source: https://www.supernova.io/blog/we-just-shipped-ai-context-management

### Skills, rules and knowledge files shipped via exporters

Audience: builders

Beyond raw data, Supernova lets DS teams author “knowledge files, rules, and custom skills” and “Ship them through predefined or custom exporters when ready”, so the platform becomes the distribution channel for agent rule files (Cursor rules / skills) into consumer repos, alongside token/code exporters for iOS, Android, React Web, React Native, Flutter.

Link: https://www.supernova.io/blog/we-just-shipped-ai-context-management

### Prototyping contexts — locked design system settings for AI generation

Audience: builders

Reusable configuration templates for Portal prototypes that pin the design system + dataset, component library (standard or custom enterprise), theme and icon pack, plus “Custom knowledge” providing “additional context, guidelines, or data for Supernova AI to consider” (what you’re building, who it’s for, core problems, platform, constraints, brand voice, API schemas). Once saved, the DS/component-library/icon-pack settings are locked and only the theme is editable, a hard constraint on what an AI prototype can reach for. Versioning caveat: new context versions apply only to newly created prototypes.

Link: https://learn.supernova.io/latest/portal/create/prototyping-contexts-jppeqv9d

### Marketing-side llms.txt + /for-ai index

Audience: consumers

Supernova publishes a curated llms.txt at the site root as a “machine-readable index” of key resources plus a human-readable /for-ai page. This is corporate-site context, not per-customer design-system context; do not confuse it with zeroheight’s per-styleguide Markdown export.

Link: https://www.supernova.io/llms.txt

```markdown
# Supernova.io

> Supernova.io is the agentic design system platform that turns your tokens, components, documentation, and code patterns into connected intelligence — so your team and their AI agents build from the same source of truth.

Supernova is a design system and knowledge management platform for product teams: design system management, documentation, code automation, and design & engineering context ready for AI agents — connected to your tokens, components, and brand.

## Core

- [Homepage](https://www.supernova.io): Overview of Supernova — the design system and knowledge management platform that keeps product teams and their AI agents working from a single source of truth.

[...]

- [For AI agents](https://www.supernova.io/for-ai): Human-readable overview of key Supernova pages for LLMs and AI crawlers.
```

Source: https://www.supernova.io/llms.txt

### Read-only boundary + OAuth/SSO auto-provisioning caveat

Audience: both

Relay is discovery/retrieval only: it “can’t make changes to data inside Supernova”. Auth is an “authenticated OAuth flow, so only folks authorised under your design system can get in”, with access revoked immediately on user removal. Governance caveat worth flagging to security teams: for SSO teams, anyone who connects through MCP OAuth is automatically added to the workspace if they were not already a member.

Link: https://learn.supernova.io/latest/releases/september-2025/introducing-supernova-relay-lWfNcpwJ

## Adoption by design systems

No publicly documented design system was found naming Supernova Relay/MCP or AI Contexts in its own docs. Supernova’s own learn.supernova.io site is itself built on Supernova and is the only observable dogfooding example. Supernova publishes a customers page and cites a Fortune-scale customer base generally, but no company has publicly published a Supernova MCP endpoint or AI-context configuration that I could verify. Treat adoption evidence as vendor-side only.

## Sources (9)

- https://www.supernova.io/llms.txt

- https://www.supernova.io/for-ai

- https://learn.supernova.io/latest/design-systems/features/mcp-for-design-system-LIHAMhjr-LIHAMhjr

- https://learn.supernova.io/latest/releases/september-2025/introducing-supernova-relay-lWfNcpwJ

- https://www.supernova.io/blog/we-just-shipped-ai-context-management

- https://learn.supernova.io/latest/portal/create/prototyping-contexts-jppeqv9d

- https://www.supernova.io/pricing

- https://www.supernova.io/blog/january-2026-product-updates

- https://www.supernova.io/write-with-ai

---

Generated 2026-07-28T06:01:02Z from the State of AI in Design Systems — July 2026 dataset. Index of every machine-readable file: https://state-of-ai-in-design-systems.netlify.app/llms.txt. JSON, SQLite and the MCP endpoint: https://state-of-ai-in-design-systems.netlify.app/ai.md. Kaelig Deloumeau-Prigent, CC BY 4.0.