> ## Documentation Index
> Fetch the complete documentation index at: https://docs.keenable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Getting started with the Keenable APIs

<Note>
  Keenable APIs are in Private Preview. Sign up for the waitlist [here](https://keenable.ai/signup) to get access.
</Note>

Keenable offers low-latency web search and web content access APIs. Get started by following the steps below.

<Columns cols={3}>
  <Column>
    <Card title="CLI" icon="rectangle-terminal" href="/cli">
      API access + MCP setup
    </Card>
  </Column>

  <Column>
    <Card title="REST API" icon="brackets-curly" href="/api-reference/introduction">
      Direct access to HTTP endpoints
    </Card>
  </Column>

  <Column>
    <Card title="MCP" icon="plug" href="/mcp-server">
      For agents that support MCP
    </Card>
  </Column>
</Columns>

## Create an API key

Before you can get started, you must create an API key in the [console](https://keenable.ai/console). The same key works across the CLI, REST API, and MCP server. See [Authentication](/authentication) for details.

## CLI

The fastest way to try Keenable is the CLI. The CLI can be used to access the Keenable APIs and automatically set up MCP integrations with your agents.

<CodeGroup>
  ```bash macOS / Linux theme={null}
  curl --proto '=https' --tlsv1.2 -LsSf \
    https://github.com/keenableai/keenable-cli/releases/latest/download/keenable-cli-installer.sh \
    | sh
  ```

  ```bash Homebrew theme={null}
  brew install keenableai/tap/keenable-cli
  ```

  ```powershell PowerShell theme={null}
  irm https://github.com/keenableai/keenable-cli/releases/latest/download/keenable-cli-installer.ps1 | iex
  ```

  ```bash Source theme={null}
  cargo install --git https://github.com/keenableai/keenable-cli
  ```
</CodeGroup>

See the [CLI](/cli) page for the full command reference.

## REST API

A minimal search call looks like this:

<CodeGroup>
  ```bash curl theme={null}
  curl -X POST "https://api.keenable.ai/v1/search" \
    -H "X-API-Key: <YOUR_API_KEY>" \
    -H "Content-Type: application/json" \
    -d '{ "query": "typescript best practices" }'
  ```

  ```python Python theme={null}
  import requests

  r = requests.post(
      "https://api.keenable.ai/v1/search",
      headers={"X-API-Key": "<YOUR_API_KEY>"},
      json={"query": "typescript best practices"},
  )
  for hit in r.json()["results"]:
      print(hit["title"], hit["url"])
  ```

  ```typescript TypeScript theme={null}
  const r = await fetch("https://api.keenable.ai/v1/search", {
    method: "POST",
    headers: {
      "X-API-Key": "<YOUR_API_KEY>",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({ query: "typescript best practices" }),
  });
  const { results } = await r.json();
  ```
</CodeGroup>

See the [REST API](/api-reference/search) reference for more detail.

## MCP

To add the Keenable tools to an agent via Remote MCP, you can add the following configuration:

```json theme={null}
{
  "mcpServers": {
    "keenable": {
      "url": "https://api.keenable.ai/mcp",
      "headers": {
        "X-API-Key": "<YOUR_API_KEY>"
      }
    }
  }
}
```

### Claude Code MCP

To add the Keenable search tools to Claude Code, you can issue the following command in your terminal:

```shellscript theme={null}
claude mcp add keenable \
  --transport http https://api.keenable.ai/mcp \
  --scope user \
  --header "X-API-Key: <YOUR_API_KEY>"
```

### Codex MCP

Add the following to `~/.codex/config.toml` :

```bash theme={null}
[mcp_servers.keenable]
url = "https://api.keenable.ai/mcp"
http_headers = { "X-API-Key" = "<YOUR_API_KEY>" }
```

See the [MCP reference](/mcp-server) for stdio transport, OAuth, and the full tool list.