MCP

Docs for assistants

• llms.txt: the index. Package version, install command, peer dependencies, and every page with a one-line summary.
• llms-full.txt: every guide and component page in one file, with code examples, API tables and the exported hooks and utilities.

Both files are generated from the same sources as this site when it is built, so they match the published package.

With a fetch server

Any Model Context Protocol client can read the files through the reference fetch server. Add it to the MCP configuration of your editor or agent:

{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    }
  }
}

{
  "mcpServers": {
    "fetch": {
      "command": "uvx",
      "args": ["mcp-server-fetch"]
    }
  }
}

Then ask the assistant to fetch https://sinups.github.io/ai-kit/llms-full.txt before it writes UI code. The server needs uvx from the uv Python tool.

Without MCP

Assistants that can fetch URLs on their own need no server. Add a short note to your project instructions file, for example AGENTS.md:

## UI

This project builds agent screens with @sinups/ai-kit (Mantine).
Before writing UI code, fetch https://sinups.github.io/ai-kit/llms-full.txt
and use only components, props and exports listed there.

## UI

This project builds agent screens with @sinups/ai-kit (Mantine).
Before writing UI code, fetch https://sinups.github.io/ai-kit/llms-full.txt
and use only components, props and exports listed there.

For assistants without network access, download llms-full.txt into the repository and point the note at the local file.

Context7

Context7 does not index @sinups/ai-kit yet. Until it does, use a fetch server or the project instructions below; both read the same files this site publishes.

Example prompts

• Read the AI UI Kit docs and add a full-page AgentChat with a welcome empty state: avatar, greeting and three starter actions.
• Embed ChatLauncher in the bottom-right corner of our dashboard with an unread badge, and keep the chat mounted while it is closed.
• Show the agent's file changes in DiffReview next to the chat, with accept and reject per file.
• Wrap the settings screen in AiKitProvider with the indigo accent and compact density, and add AiKitThemeCustomizer to it.
• Render our custom tool-Deploy parts with a toolRenderers entry that reports approve through onToolAction.