> For the complete documentation index, see [llms.txt](https://docs.balkan.id/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.balkan.id/balkanid-mcp/installation-and-setup/chatgpt.md).

# ChatGPT

Connect [ChatGPT](https://chat.openai.com) to BalkanID MCP using a [custom connector](https://developers.openai.com/plugins/deploy/connect-chatgpt).

**OAuth is preferred.** API keys remain available when OAuth is unavailable or you need Read-only access.

{% hint style="warning" %}
Custom MCP connectors in ChatGPT require [Developer Mode](https://developers.openai.com/api/docs/guides/developer-mode) (or equivalent connector access on your ChatGPT plan). Confirm this is allowed under your organization's AI policy before connecting to a production BalkanID tenant.
{% endhint %}

### One-click (OAuth — recommended)

1. Open <https://mcp.balkanid.app>, sign in, and confirm the correct **tenant**.
2. In **OAuth Connectors**, click **Connect to ChatGPT**.
3. Complete the [connector flow in ChatGPT](https://developers.openai.com/plugins/deploy/connect-chatgpt) when prompted.
4. Set or confirm the connector URL: `https://mcp.balkanid.app/server/mcp`
5. Complete BalkanID sign-in, pick your **tenant**, and grant consent.

{% hint style="info" %}
OAuth currently requires **both Read and Write** scopes. See Authentication and Permissions.
{% endhint %}

### Manual configuration (OAuth)

1. In ChatGPT, open **Settings** → **Connectors** ([Developer Mode](https://developers.openai.com/api/docs/guides/developer-mode) must be enabled).
2. In [ChatGPT Plugins](https://developers.openai.com/plugins/deploy/connect-chatgpt), add a **custom connector** (remote MCP / HTTP).
3. Set the URL to `https://mcp.balkanid.app/server/mcp`.
4. Complete BalkanID OAuth when ChatGPT prompts you to authenticate.

### API key fallback

When OAuth is unavailable or you need **Read-only** access:

1. Create an API key in the [MCP UI](https://mcp.balkanid.app) under **Bearer Auth Keys**.
2. Configure the connector with header `Authorization: Bearer YOUR_TOKEN_HERE` if your [ChatGPT connector setup](https://developers.openai.com/plugins/deploy/connect-chatgpt) supports custom headers.

Do not commit tokens. Prefer the shortest practical key expiry.

### Verify

Ask ChatGPT: “Call whoami on BalkanID MCP.” You should see your email and tenant ID.

### Disable or remove

Open **Settings → Connectors**, find BalkanID, and remove the connector. OpenAI does not document a separate disconnect/logout action distinct from removal — removing the connector also revokes its access.

### Official documentation

OpenAI documentation for custom MCP connectors in ChatGPT:

* [ChatGPT Developer mode](https://developers.openai.com/api/docs/guides/developer-mode) — OpenAI
* [Connect and test your plugin (MCP server)](https://developers.openai.com/plugins/deploy/connect-chatgpt) — OpenAI


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.balkan.id/balkanid-mcp/installation-and-setup/chatgpt.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.