Each context has its own MCP endpoint. When you distribute via MCP, AI tools receive exactly the data scoped in that context — tokens, documentation, components, files, and skills — nothing more.
Users need a Supernova account to connect.
Get the context MCP URL
- In Contexts section, open the context.
- Go to the Distribution section.
- Copy the MCP URL from the MCP card.
The URL follows this format:
https://mcp.supernova.io/mcp/c/{ID}-{context-name}
Connect in your AI tool
- CTRL/CMD + , to open Cursor settings.
- Navigate to MCP & Integrations.
- Select New MCP Server → Add a Custom MCP Server.
- Paste the following JSON into the mcp.json that will open:
{
"mcpServers": {
"supernova": {
"url": "https://mcp.supernova.io/mcp/c/{ID}-{context-name}",
}
}
}
Replace the {ID} with a context ID you want to use in your specific project.
- CTRL/CMD + SHIFT + P and search for MCP: Add Server.
- Select HTTP (HTTP or Server-Sent Events).
- Enter the following URL:
https://mcp.supernova.io/mcp/c/{ID}-{context-name}
- Enter the name Supernova and hit enter.
- Activate the server using MCP: List Servers and selecting Supernova, and selecting Start Server.
- Complete login flow in the browser.
Replace the {ID} with a desired context ID you want to use in your specific project.
- CTRL/CMD + , to open Windsurf settings.
- Under Scroll to Cascade → MCP servers
- Select Add Server → Add custom server
- Add the following:
{
"mcpServers": {
"supernova": {
"url": "https://mcp.supernova.io/mcp/c/{ID}-{context-name}",
"type": "http"
}
}
}
Replace the {ID} with a desired context ID you want to use in your specific project.
Team, Enterprise (Claude.ai)
- Navigate to Settings in the sidebar on web or desktop
- Scroll to Connectors at the bottom and click Add more
- In the prompt enter:
- Integration name: Supernova
- Integration URL: https://mcp.supernova.io/mcp/c/{ID}-{context-name}
- Make sure to enable the tools in any new chats
Claude for Desktop
- Open the file ~/Library/Application Support/Claude/claude_desktop_config.json
- Add the following and restart the Claude desktop app:
{
"mcpServers": {
"supernova": {
"url": "https://mcp.supernova.io/mcp/c/{ID}-{context-name}",
"type": "http"
}
}
}
Replace the {ID} with a desired context ID you want to use in your specific project.
Feedback collection
Feedback collection lets MCP consumers report context quality issues directly from their AI tool. Feedback is tied to this context and visible in Supernova so you can act on it.
You can enable feedback collection in the MCP card under Distribution.
Learn how to configure and review feedback
Best practices
Share the MCP URL only with the team this context is scoped for. If you have separate contexts for engineering and marketing, each team should connect to their respective endpoint — not a shared one.
Review feedback regularly. It's the fastest signal for gaps between what AI tools are doing and what your design system defines.
If a team's AI tool is consistently returning wrong or outdated information, check whether the context scope includes the right token groups and documentation pages for their use case.
Tool function list
The following functions are available when connected to a context endpoint. They come with sufficient descriptions such that AI tools automatically pick up when to use them without additional prompting.
|
Tool |
Description |
|---|---|
|
get_token_list |
Pulls the list of design tokens scoped in the context, including values, references, and groupings. |
|
get_token_details |
Fetches full details for a specific design token. |
|
get_token_theme_list |
Lists the token themes available in the context. |
|
get_documentation_page_list |
Lists documentation pages scoped in the context, including titles, slugs, and hierarchy. |
|
get_documentation_page_content |
Grabs the content of a specific documentation page, formatted as markdown. |
|
search_documentation |
Searches across documentation content scoped in the context. |
|
get_figma_component_list |
Returns a list of all Figma components, with key info like names, IDs, and categories. |
|
get_figma_component_detail |
Retrieves full details on a Figma component, including its structure and variants. |
|
get_design_system_component_list |
Lists metadata for all components, giving an overview of the component library. |
|
get_design_system_component_detail |
Provides metadata details for a component, like its status, tags, and cross-references. |
|
get_code_component_list |
Lists code components available in the context. |
|
get_code_component_detail |
Fetches details for a specific code component. |
|
get_storybook_story_list |
Lists Storybook stories connected to the design system. |
|
get_storybook_story_detail |
Fetches details of a specific Storybook story. |
|
get_asset_list |
Pulls a list of all assets, including names and types. |
|
get_asset_detail |
Fetches detailed info about a specific asset, like its properties and metadata. |
|
get_knowledge_file_list |
Lists workspace files attached to the context. |
|
get_knowledge_file_detail |
Fetches the content of a specific attached file. |
|
get_knowledge_skill_list |
Lists workspace skills attached to the context. |
|
get_knowledge_skill_detail |
Fetches the content of a specific attached skill. |
|
collect_agent_feedback |
Submits context-tied feedback, available when feedback collection is enabled. |
|
get_me |
Checks which account you are logged in to. |