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

# Manage Kataven with AI — Claude, ChatGPT, Codex, Cursor

> Drive your Kataven account from Claude Code, Claude Desktop, ChatGPT, Codex, Cursor, or any other AI tool. Pick the right integration path — SDK or MCP — for your tool, then jump to the focused guide.

You can run your entire Kataven account from an AI tool — create agents, configure tools, place calls, run campaigns — without writing API code yourself. The right integration path depends on whether your AI tool has a **shell** (can run `python my_script.py`) or is **chat-only**.

## Pick your path

| Your AI tool                             | Has a shell? | Use        | Guide                                                                                    |
| ---------------------------------------- | ------------ | ---------- | ---------------------------------------------------------------------------------------- |
| **Claude Code**                          | Yes          | Python SDK | [Manage with Claude Code →](/guides/manage-with-claude-code)                             |
| **Codex CLI**                            | Yes          | Python SDK | [Manage with Codex →](/guides/manage-with-codex)                                         |
| **Cursor** (composer / agent mode)       | Yes          | Python SDK | Same as Claude Code — Cursor runs `python` for you                                       |
| **Claude Desktop**                       | No           | MCP server | [Manage with Claude Desktop →](/guides/manage-with-claude-desktop)                       |
| **ChatGPT Desktop**                      | No           | MCP server | [Manage with ChatGPT →](/guides/manage-with-chatgpt)                                     |
| **OpenAI Agents SDK** (programmatic)     | N/A          | MCP server | [Manage with ChatGPT § OpenAI Agents SDK](/guides/manage-with-chatgpt#openai-agents-sdk) |
| **n8n / Zapier with an LLM step**        | No           | MCP server | Same install as Claude Desktop                                                           |
| **Custom agent** (LangGraph, Agno, etc.) | Either       | Either     | MCP is easier to plug in                                                                 |

## Why two paths?

The Kataven Hub API is just HTTP. Anything that can speak HTTP can drive it.

* **AI tools with a shell** install the [Python SDK](/sdks/python/overview) (`pip install kataven`) and let the AI write & run Python directly. No middleware. The SDK is the headless surface.
* **Chat-only AI tools** install the [Kataven MCP server](/sdks/mcp/overview) (`pip install kataven-mcp`), which exposes every SDK verb as an MCP tool the AI can call from inside its chat loop. The MCP server is a thin wrapper around the SDK — same functionality, different protocol.

You don't need both for the same client. Pick one.

## Common setup (any path)

All four guides start the same way:

<Steps>
  <Step title="Mint an API key">
    [hub.kataven.ai/settings](https://hub.kataven.ai/settings) → **API Keys** tab → **Create API key**. Copy the `sk_live_…` value once. Full walkthrough: [Quickstart § 1](/quickstart#1-mint-an-api-key).
  </Step>

  <Step title="Install the SDK or MCP server">
    Per-tool details in the guides below. Both ship as standard pip packages.
  </Step>

  <Step title="Configure your AI tool">
    Set `KATAVEN_API_KEY=sk_live_…` somewhere the tool can read it (env var for shell-based tools, MCP config file for chat-only tools).
  </Step>
</Steps>

## What the AI can actually do

Every Hub API verb is reachable. Concretely:

* `kataven_list_agents`, `kataven_get_agent`, `kataven_create_agent`, `kataven_update_agent`, `kataven_delete_agent`
* `kataven_attach_playbook` / `kataven_detach_playbook`, `kataven_attach_faq` / `kataven_detach_faq`
* `kataven_list_tools`, `kataven_create_tool` (custom tools)
* `kataven_list_phone_numbers`, `kataven_create_phone_number`, `kataven_update_phone_number`
* `kataven_originate_call` (place outbound test calls)
* `kataven_list_campaigns`, `kataven_create_campaign`, `kataven_start_campaign`, `kataven_pause_campaign`, `kataven_stop_campaign`
* `kataven_list_widget_keys`, `kataven_create_widget_key`
* ...and the full surface of [the API reference](/api-reference/introduction).

A few admin endpoints stay out of reach by design (cost-cap edits, integration authoring, recording deletion) — those require a Hub UI session, and the server returns `403` to `sk_live_` callers. See [Authentication § Mint, list, revoke API keys](/authentication).

## Pick your guide

<CardGroup cols={2}>
  <Card title="Claude Code" icon="terminal" href="/guides/manage-with-claude-code">
    Anthropic's terminal coding agent. Has a shell, uses the SDK directly, no MCP needed.
  </Card>

  <Card title="Claude Desktop" icon="message" href="/guides/manage-with-claude-desktop">
    The chat-only Claude desktop app. Wires up via MCP server in `claude_desktop_config.json`.
  </Card>

  <Card title="ChatGPT" icon="comment" href="/guides/manage-with-chatgpt">
    ChatGPT Desktop via MCP, or the OpenAI Agents SDK programmatically.
  </Card>

  <Card title="Codex CLI" icon="code" href="/guides/manage-with-codex">
    OpenAI's terminal coding agent. Has a shell, uses the SDK directly.
  </Card>
</CardGroup>