Display components

Register React components that your agent can render in the chat.

Tool-Based Generative UI

Waking up the demo

What is this?

A display component is a React component that your agent can call as a tool. When the agent calls the tool, CopilotKit renders your component directly in the chat with the tool's arguments as props. You do not write a handler, and the user does not need to do anything.

import { useComponent } from "@copilotkit/react-core/v2";
import { Chart, ChartProps } from "./chart";

useComponent({
name: "showChart",
description: "Populate data and show the user a chart",
parameters: ChartProps,
render: Chart
});

When should I use this?

Use a display component when you want to:

  • Display rich UI (cards, charts, tables) inline in the chat
  • Show structured data from agent responses
  • Render previews, status indicators, or visual feedback
  • Let the agent present information beyond plain text

How it works in code

Forward browser tools to Claude

Frontend tools registered with useFrontendTool arrive in the AG-UI run input. This demo's server calls the Anthropic Messages API directly for runs that carry frontend tools, so it converts each AG-UI tool definition into a Messages API tool schema first.

The published ClaudeAgentAdapter from ag_ui_claude_sdk needs no such conversion. It registers each frontend tool on its own in-process MCP tool server as mcp__ag_ui__<name>, allows it, and ends the run when Claude calls it so the browser can execute the tool. Pass the run input to the adapter and frontend tools work with no extra wiring.

agent.py
def _build_frontend_tools(input_data: RunAgentInput) -> list[dict[str, Any]]:
    """Extract frontend-defined tools from the AG-UI request.

    The CopilotKit runtime forwards frontend tool definitions (registered
    via ``useFrontendTool``, ``useHumanInTheLoop``, etc.) in
    ``input_data.tools``. We convert them to the Anthropic ``tools``
    schema so the LLM can call them. The runtime intercepts the resulting
    tool-call events and routes them to the frontend for resolution.
    """
    out: list[dict[str, Any]] = []
    for t in input_data.tools or []:
        name = getattr(t, "name", None) or (
            t.get("name") if isinstance(t, dict) else None
        )
        description = getattr(t, "description", None) or (
            t.get("description", "") if isinstance(t, dict) else ""
        )
        parameters = getattr(t, "parameters", None) or (
            t.get("parameters", {}) if isinstance(t, dict) else {}
        )
        if not name:
            continue
        out.append(
            {
                "name": name,
                "description": description or "",
                "input_schema": parameters or {"type": "object", "properties": {}},
            }
        )
    return out

The display component receives the tool's arguments as typed props and mounts inline in the chat. Below is the bar chart from the demo. The agent sends the data, and the component draws it.

page.tsx
  useComponent({
    name: "render_bar_chart",
    description: "Display a bar chart with labeled numeric values.",
    parameters: barChartPropsSchema,
    render: BarChart,
  });

Ask the agent for a chart, for example Show me a bar chart of quarterly sales for Q1, Q2, Q3, Q4. The chart renders in the chat with the data that the agent filled in.

Without parameters

For simple components that don't need typed parameters, leave out parameters. The component then accepts any props:

useComponent({
  name: "showGreeting",
  render: ({ message }: { message: string }) => (
    <div className="rounded border p-3 bg-blue-50">
      <p>{message}</p>
    </div>
  ),
});

Scoping to an agent

In multi-agent setups, pass agentId to scope a component to one agent:

useComponent({
  name: "renderProfile",
  parameters: z.object({ userId: z.string() }),
  render: ProfileCard,
  agentId: "support-agent",
});

How is this guide?