# Components as Tools

> Let your agent render rich React components directly in the chat by calling them as tools.

<!-- interactive demo: gen-ui-tool-based -->

## What is this? [#what-is-this]

Tool-based Generative UI is the simplest form of Generative UI: you register
a React component with `useComponent`, and CopilotKit exposes it to the
agent as a tool. When the agent calls the tool, CopilotKit renders your
component inline in the chat, passing the tool's arguments straight through
as typed props.

Unlike [tool rendering](/langgraph-python/generative-ui/tool-rendering), which wraps a
real backend tool in a custom UI, tool-based GenUI is the component. There
is no handler, no user interaction, no server-side execution. The agent
decides when to show it, populates the data, and CopilotKit renders it.

## When should I use this? [#when-should-i-use-this]

Use `useComponent` when you want to:

- Display rich UI (cards, charts, tables, dashboards) inline in the chat
- Show structured data the agent has derived from its reasoning
- Render previews, status indicators, or visual summaries
- Let the agent present information beyond plain text

For components that need user interaction, see
[Human-in-the-loop](/langgraph-python/human-in-the-loop). For operational transparency
around a real backend tool, see [Tool rendering](/langgraph-python/generative-ui/tool-rendering).

## How it works in code [#how-it-works-in-code]

<Steps>
  <Step>
    ### Install the LangGraph Python SDK

    <Tabs className="p-0 m-0" groupId="python-pm" items={['uv', 'poetry', 'pip', 'conda']} default="uv">
    <Tab value="uv">
    ```bash
    uv add copilotkit
    ```
    </Tab>
    <Tab value="poetry">
    ```bash
    poetry add copilotkit
    ```
    </Tab>

    <Tab value="pip">

    ```bash
    pip install copilotkit --extra-index-url https://copilotkit.gateway.scarf.sh/simple/
    ```
    </Tab>

    <Tab value="conda">
    ```bash
    conda install copilotkit -c copilotkit-channel
    ```
    </Tab>

</Tabs>

  </Step>
  <Step>
    ### Wire CopilotKit middleware into your graph

    Frontend tools registered with `useFrontendTool` are forwarded to your
    agent at runtime. `CopilotKitMiddleware` is the bridge — drop it into
    `create_agent`'s `middleware` list and the LLM sees the forwarded tool
    definitions on every turn.

~~~~python title="frontend_tools.py"
from langchain.agents import create_agent
from langchain_openai import ChatOpenAI
from copilotkit import CopilotKitMiddleware

graph = create_agent(
    model=ChatOpenAI(reasoning_effort="none", model="gpt-6-luna"),
    tools=[],
    middleware=[CopilotKitMiddleware()],
    system_prompt="You are a helpful, concise assistant.",
)
~~~~

  </Step>
  <Step>
    ### Using a custom graph instead of `create_agent`

    `CopilotKitMiddleware` only works with `create_agent`. In a graph where you
    define the nodes and edges yourself, the forwarded tools sit in
    `state["copilotkit"]["actions"]`, and the model can call them only after
    you bind them. Inherit your state from `CopilotKitState`:

    ```python title="agent.py"
    from copilotkit import CopilotKitState

    class AgentState(CopilotKitState):
        pass
    ```

    Then bind the actions to the model in your agent node:

    ```python title="agent.py"
    from langchain_core.runnables import RunnableConfig
    from langchain_openai import ChatOpenAI

    async def agent_node(state: AgentState, config: RunnableConfig):
        # Access the tools from the copilotkit property
        tools = state.get("copilotkit", {}).get("actions", [])
        model = ChatOpenAI(model="gpt-6-luna", reasoning_effort="none").bind_tools(tools)

        # ...
    ```

  </Step>
</Steps>

The built-in agent needs no backend step. Import the hook and Zod in the
component that registers the tool:

```tsx
import { useComponent } from "@copilotkit/react-core/v2";
import { z } from "zod";
```

`useComponent` takes a name, a Zod schema for its props, and the component
to render. The hook registers it as a frontend tool, so the agent can call
it. The schema becomes the tool's parameters, which tell the model which
arguments to send.

<Callout type="warn">
  `parameters` is optional, but leaving it out advertises the tool with an
  empty parameter schema (`{ "type": "object", "properties": {} }`). The model
  then has nothing to fill in, so it calls the tool with no arguments and your
  component renders with no props. Pass a schema for any component that needs
  data.
</Callout>

Define the props of your component as a Zod schema:

```tsx title="bar-chart.tsx"
import { z } from "zod";

export const barChartPropsSchema = z.object({
  title: z.string().describe("Chart title"),
  description: z.string().describe("Brief description or subtitle"),
  data: z.array(
    z.object({
      label: z.string(),
      value: z.number(),
    }),
  ),
});
```

Pass the schema and your component to `useComponent`:

```typescript title="src/app/demos/gen-ui-tool-based/page.tsx"
  useComponent({
    name: "render_bar_chart",
    description: "Display a bar chart with labeled numeric values.",
    parameters: barChartPropsSchema,
    render: BarChart,
  });
```

`BarChart` is your own React component. It reads only its props and can
stream in as the agent fills the payload. The demo builds it with
[Recharts](https://recharts.org). It does not know anything about CopilotKit.

<Callout type="info">
  The `name` you pass to `useComponent` is what the agent sees as the tool
  name. Make it a verb like `render_bar_chart` or `show_weather` so the LLM
  reliably picks it when the user asks for that visualization.
</Callout>

To check it, ask the agent for a bar chart of quarterly sales. The bar chart
renders inline in the chat with the data from the agent.

## Rendering in a headless chat [#rendering-in-a-headless-chat]

CopilotKit's built-in chat components render registered components for you. A
headless or custom chat renders the message list itself, so no tool call
renders unless you render it. The component is registered and the agent
calls it, but the chat stays empty.

Render the tool calls on each assistant message with
`CopilotChatToolCallsView`:

```tsx
import { CopilotChatToolCallsView } from "@copilotkit/react-core/v2";

<CopilotChatToolCallsView message={assistantMessage} messages={allMessages} />;
```

It looks up the sibling `tool`-role message for each tool call and hands both
to the registered renderer. For finer placement, call `useRenderToolCall()` and
render each tool call yourself. See
[Headless UI](/langgraph-python/custom-look-and-feel/headless-ui).

<IntegrationGrid path="generative-ui/tool-based" />
