- Accordion
- Attachment
- Avatar
- Badge
- Breadcrumb
- Button
- Button Group
- Card
- Checkbox
- Code Block
- Collapsible
- Dialog
- Dropdown Menu
- Empty
- Field
- Hover Card
- Input
- Input Group
- Input OTP
- Item
- Label
- Marker
- Message
- Number Flow
- Pagination
- Popover
- Progress
- Radio Group
- Select
- Slider
- Sonner
- Spinner
- Switch
- Tooltip
- Separator
- Sheet
- Tabs
- Textarea
- Toggle
- Toggle Group
- Trace
Agents
What an AI agent sees when it builds with Frakment. Real MCP tool calls, real responses, no hand-waving.
Frakment ships an MCP server and an agent skill. Agents can compose, install, and use the registry without a human in the loop.
The workflow
Agent calls compose with a scenario name
MCP returns the components that fit that UI pattern.
Agent calls get_install_command with the primary component
MCP returns the npx command that installs it and pulls its registryDependencies.
User runs one command
The rest lands automatically. No manual dependency resolution, no guessing slugs.
Chat UI
Prompt: "Build a chat interface with auto-scroll"
The agent calls compose:
{
"tool": "compose",
"arguments": { "scenario": "chat" }
}MCP responds:
# chat
Chat interface with auto-scroll and animated turns
Components: bubble, message, message-scroller, avatar, message-animated
Install: npx frakment@latest add message-animatedThe agent calls get_install_command:
{
"tool": "get_install_command",
"arguments": { "name": "message-animated" }
}MCP responds:
$ bunx --bun frakment@latest add message-animated$ npx frakment@latest add message-animated$ pnpm dlx frakment@latest add message-animated$ yarn dlx frakment@latest add message-animated
That single command pulls bubble, message-scroller, and the AI engine via registryDependencies.
Agent timeline
Prompt: "Build an agent timeline with reasoning steps"
The agent calls compose:
{
"tool": "compose",
"arguments": { "scenario": "agent-timeline" }
}MCP responds:
# agent-timeline
Agent reasoning timeline with status and command output
Components: trace, code-block, chain-of-thought, pulse
Install: npx frakment@latest add trace code-blockThe agent calls get_install_command:
{
"tool": "get_install_command",
"arguments": { "name": "trace" }
}MCP responds:
$ bunx --bun frakment@latest add trace code-block$ npx frakment@latest add trace code-block$ pnpm dlx frakment@latest add trace code-block$ yarn dlx frakment@latest add trace code-block
trace pulls code-block as a registry dependency. Add chain-of-thought and pulse separately.
Login form
Prompt: "Build an accessible login form"
The agent calls compose:
{
"tool": "compose",
"arguments": { "scenario": "login-form" }
}MCP responds:
# login-form
Accessible login form with remember-me toggle
Components: field, label, input, button, checkbox
Install: npx frakment@latest add fieldThe agent calls get_install_command:
{
"tool": "get_install_command",
"arguments": { "name": "field" }
}MCP responds:
$ bunx --bun frakment@latest add field$ npx frakment@latest add field$ pnpm dlx frakment@latest add field$ yarn dlx frakment@latest add field
field pulls label and separator. Add input, button, and checkbox separately.
All scenarios
| Scenario | What you get | Entry |
|---|---|---|
chat | Chat UI with auto-scroll, avatar, and animated turns | message-animated |
agent-timeline | Reasoning timeline with status, pulse, and command output | terminal |
login-form | Accessible form with field, label, input, button, and checkbox | field |
settings-panel | Settings view with toggles, grouped options, and separators | toggle-group |
search-input | Search field with inline button and loading state | input-group |
status-dashboard | Service health overview with daily timeline and badges | pulse |
Call list_scenarios with no input to get the current set. The tool is the source of truth so the list stays current.
Connect your agent
See MCP server for the stdio config and the full tool list. See Skills for the load-on-demand skill that teaches agents when to use the registry.