# ChatGPT

Connect Dstl8 to ChatGPT via MCP for observability access in chat.

### Prerequisites

* ChatGPT Plus, Team, or Enterprise plan
* Your [MCP endpoint and API token](/controltheory-documentation/dstl8-docs/mcp-integration.md)

### Setup

1. Open ChatGPT and go to **Settings → Connectors → Add custom connector**
2. Enter the following:
   * **Name:** Dstl8
   * **URL:** `https://<org_id>.app.dstl8.ai/mcp`
   * **Authentication:** Bearer token
   * **Token:** your Dstl8 API token
3. Click **Save**

Replace `<org-id>` and token with your credentials.

### Verify

Start a new conversation and ask ChatGPT to list your available tools. You should see the Dstl8 observability tools listed.

### Troubleshooting

**Connector not connecting** — Verify your endpoint is reachable by running in a terminal:

```bash
curl -I -H "Authorization: Bearer <your-token>" \
  https://<org_id>.app.dstl8.ai/mcp
```

A `401` means the token is invalid. A `200` or `400` means the endpoint is reachable and the issue is on the ChatGPT side.

> **Note:** ChatGPT MCP support is relatively new and connector behavior may vary. If you run into issues, reach out to us at <support@controltheory.com>.


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.controltheory.com/controltheory-documentation/dstl8-docs/mcp-integration/chatgpt.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.