> This page is for version v1.0.1 (default).
> For other versions, use one of these documentation indexes:
> - v1.0.1 (default): https://docs.kinetk.ai/v-1-0-1/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.kinetk.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.kinetk.ai/_mcp/server.

# Connect KINETK to Your AI Assistant

> Set up the hosted KINETK MCP in Claude, ChatGPT, Cursor, Codex, Gemini or Grok. Nothing to install.

Your AI assistant is great at reasoning, but it doesn't know what's trending on TikTok this morning, which creators are driving a narrative, or how a hashtag is performing across platforms. KINETK does.

With one quick setup, you can connect KINETK to the AI assistant you already use — Claude, ChatGPT, Cursor, and others. Once connected, just talk to your assistant in plain English, and **mention "kinetk"** when you want live intelligence.

> *"What's trending in the World Cup right now?"*
> *"Which creators are driving the luxury-watch conversation this month?"*
> *"Pull the top posts about sustainable sneakers so I can cite them."*

You ask. KINETK answers.

---

## Pick your assistant

Quick setup examples — choose the one you already use. They all reach the same KINETK Knowledge Graph and bill the same account.

| Method                 | Assistants                                                               | How you authenticate                                                                                      |
| ---------------------- | ------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------- |
| **Sign in (OAuth)**    | **Claude Desktop**, **ChatGPT**                                          | Paste the sign-in address, then sign in with your KINETK login. No key to copy.                           |
| **API key**            | **Claude Code**, **Codex**, **Cursor**, **Gemini/Antigravity**, **Grok** | Paste your KINETK `x-api-key`.                                                                            |
| **OAuth via your IdP** | **Gemini Enterprise** (Agentspace)                                       | Admin setup through your identity provider. See [Gemini Enterprise](#gemini-enterprise-custom-mcp) below. |

> ⚠️ The sign-in method uses the **sign-in address** (`…/graph/connect`); the API-key method uses the **MCP address** (`…/graph/mcp`). Claude Desktop's custom connector can't send an API-key header — always use the sign-in address there.

### Claude Desktop — Desktop App

Add KINETK as a custom connector inside the Claude app.

1. Open **Settings → Connectors → Add custom connector**.
2. Paste the sign-in address into the connector URL field: `https://api.kinetk.ai/graph/connect`
3. Save, then click **Connect / Sign in** — a browser opens to the KINETK login. Sign in and approve.
4. KINETK shows as connected, and the tools appear near the message box.

### ChatGPT — Web App

Add KINETK as an app inside ChatGPT on the web.

1. Open ChatGPT on the web. This setup isn't available in the mobile or desktop apps, and requires a paid ChatGPT plan.
2. Go to **Settings → Apps → Advanced settings** and turn **Developer mode** on.
3. Click **Create App**, paste the sign-in address `https://api.kinetk.ai/graph/connect`, then click **Create**.
4. Sign in with KINETK and the tools are ready.

### Claude Code — CLI

Register the KINETK MCP server from your terminal.

1. Run the command below, replacing `YOUR_KEY` with your KINETK API key.
2. Restart Claude Code — the kinetk tools load automatically.

```bash
claude mcp add --transport http kinetk https://api.kinetk.ai/graph/mcp --header "x-api-key: YOUR_KEY"
```

### Codex — CLI

Add the KINETK MCP server to your Codex config.

1. Open `~/.codex/config.toml` on Linux/macOS (`$HOME/.codex/config.toml` on Windows).
2. Add the config below to the bottom of the file.
3. Replace the `API_KEY` placeholder with your KINETK API key.
4. Start Codex and verify with the `/mcp` command.

```toml
[mcp_servers.kinetk]
url = "https://api.kinetk.ai/graph/mcp"
enabled = true
startup_timeout_sec = 30

[mcp_servers.kinetk.http_headers]
"x-api-key" = "API_KEY"
```

### Cursor — IDE

Add KINETK under Tools & MCPs in Cursor settings.

1. Open **Settings → Tools & MCP → New MCP Server** or **Add Custom MCP**.
2. Paste the JSON below into `mcp.json`.
3. Change the `api-key` placeholder to your KINETK API key.
4. Refresh — the kinetk tools become available.

```json
{
  "mcpServers": {
    "kinetk": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.kinetk.ai/graph/mcp",
        "--header",
        "x-api-key:${KINETK_KEY}"
      ],
      "env": {
        "KINETK_KEY": "api-key"
      }
    }
  }
}
```

### Gemini / Antigravity — CLI

Add the KINETK MCP server to your Gemini config.

1. Open `~/.gemini/config/mcp_config.json` on macOS (`$HOME/.gemini/config/mcp_config.json` on Windows).
2. Paste the JSON below into the file.
3. Replace the `API_KEY` placeholder with your KINETK API key.
4. Launch Antigravity (`agy`) and verify with the `/mcp` command.

```json
{
  "mcpServers": {
    "kinetk": {
      "serverUrl": "https://api.kinetk.ai/graph/mcp",
      "headers": {
        "x-api-key": "API_KEY"
      }
    }
  }
}
```

> **Note:** the consumer **Gemini app** (gemini.google.com / mobile) can't add custom MCP connectors yet — use the config above, or **Gemini Enterprise** below.

### Grok — CLI

Register the KINETK MCP server from your terminal.

1. Run the commands below for your OS, replacing `API_KEY` with your KINETK API key.
2. Start Grok and verify with the `/mcp` command.

**macOS / Linux:**

```bash
export KINETK_API_KEY="API_KEY"
grok mcp add --transport http kinetk https://api.kinetk.ai/graph/mcp --header "x-api-key: ${KINETK_API_KEY}"
```

**Windows:**

```powershell
$env:KINETK_API_KEY="API_KEY"
grok mcp add --transport http kinetk https://api.kinetk.ai/graph/mcp --header "x-api-key: $env:KINETK_API_KEY"
```

Need a key? Get one from the [platform portal](https://platform.kinetk.ai) or contact the KINETK team.

### Gemini Enterprise (custom MCP)

[Gemini Enterprise](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/custom-mcp-server/set-up-custom-mcp-server) (Agentspace) connects to KINETK as a **custom MCP data store**. It uses **OAuth 2.0** through your own identity provider — there's no API-key option here — and only the **StreamableHTTP** transport (point it at the `…/mcp` address, not `…/connect`).

This is an admin-driven setup, not a one-click connect:

1. **Prerequisites.** Have an Organization Policy Administrator enable custom MCP servers (it's off by default), and grant your account the **Discovery Engine Editor** (`roles/discoveryengine.editor`) role.

2. **Register Gemini Enterprise as an OAuth client** with your IdP (Okta, Azure AD, Google, …), setting the authorization redirect URL to `https://vertexaisearch.cloud.google.com/oauth-redirect`. Note the resulting **Client ID**, **Client Secret**, **Authorization URL**, **Token URL** and **Scopes**.

3. **Add the server.** In the Google Cloud console → **Gemini Enterprise → Data stores → Create data store**, search **Custom MCP Server (Preview)**, and choose **Add MCP server**.

4. **Fill the MCP Server Configuration:**

   | Field                                 | Value                                             |
   | ------------------------------------- | ------------------------------------------------- |
   | **MCP Server URL**                    | `https://api.kinetk.ai/graph/mcp`                 |
   | **Authorization URL** / **Token URL** | from your OAuth registration (step 2)             |
   | **Client ID** / **Client Secret**     | from your OAuth registration (step 2)             |
   | **Scopes**                            | space-separated list from step 2                  |
   | **MCP Server Description**            | e.g. "KINETK social-media narrative intelligence" |

5. **Save** and complete the OAuth consent. The KINETK tools become available to your Gemini Enterprise agents.

The OAuth endpoints and client credentials are issued by KINETK — contact the KINETK team to provision them for your organization.

---

## How to use it

Once connected, just talk to your assistant and **mention "kinetk"** when you want live intelligence. See [What You Can Ask](/documentation/mcp-server/what-you-can-ask) for example prompts and what each one costs.

---

## Tips for better answers

* **Say "kinetk."** Without the cue your assistant may answer from general knowledge and skip the live data.
* **Be specific.** "Trends in women's football on TikTok this week" beats "sports trends."
* **Heavier questions take a moment.** Quick content lookups return in seconds; deeper trend analysis can take up to a minute — your assistant waits and then answers.

---

## About your account and usage

Whether you sign in or use an API key, usage counts against your KINETK account. Pulling content and running analyses uses credits; simply being connected doesn't. See [Pricing & Credits](/documentation/get-started/pricing-credits). Keep your API key private — treat it like a password.

---

## Troubleshooting

* **Assistant answers without using KINETK** → add "use kinetk" and confirm the connector shows connected.
* **Claude Desktop "couldn't connect to the server"** → make sure you used the **sign-in** address (`…/graph/connect`), not the API-key address. Desktop can't send a key header.
* **"Unauthorized"** on the API-key method → check the address and that `x-api-key` has no stray spaces.
* **Not enough credits** → buy credits on the [billing page](https://platform.kinetk.ai/billing).
* **A trend question is slow** → deeper analysis runs a fuller pipeline; give it up to a minute.