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

# ChatGPT

> Connect StackOne MCP to ChatGPT as a custom connector.

## Overview

[ChatGPT](https://chatgpt.com) connects to remote MCP servers as **custom connectors**. Once added, StackOne's actions are available as tools in your chats.

<Info>
  Custom MCP connectors require Developer Mode and are available on paid ChatGPT plans (Plus, Pro, Business, Enterprise, Edu). Availability and steps change often — see OpenAI's [connectors documentation](https://help.openai.com/en/articles/11487775-connectors-in-chatgpt) for the current flow.
</Info>

## Setup

StackOne's MCP endpoint is a remote, Streamable HTTP server:

```
https://api.stackone.com/mcp
```

<Steps>
  <Step title="Get your MCP URL">
    In the StackOne dashboard, open a connector, click **Use in Agent**, select a linked account, and copy the generated token URL (`https://api.stackone.com/mcp?token=...`).
  </Step>

  <Step title="Add it as a custom connector">
    In ChatGPT, enable **Developer Mode**, then go to **Settings → Connectors → Create** and paste the StackOne MCP URL. ChatGPT handles the connection over Streamable HTTP — no `mcp-remote` wrapper needed.
  </Step>

  <Step title="Use it in a chat">
    Start a new chat, enable the StackOne connector, and try:

    ```text theme={null}
    What StackOne tools are available?
    ```
  </Step>
</Steps>

## Handling large tool catalogs

If the connector exposes many actions, add the `tool-mode=search_execute` query parameter to the MCP URL in your config. The client then registers just two tools — search + execute — and the agent discovers actions at runtime, so the context footprint stays flat however large the catalog:

```
https://api.stackone.com/mcp?tool-mode=search_execute
```

For a token URL, append it as an extra parameter: `https://api.stackone.com/mcp?token=<session_token>&tool-mode=search_execute`.

See [Tool Discovery](/features/tool-discovery) for how search works, its accuracy, and the other modes.

## Optimize and secure

With your agent connected, use StackOne's platform features to optimize performance and secure every call.

<CardGroup cols={3}>
  <Card title="Search & Execute" icon="magnifying-glass" href="/optimize/search-and-execute">
    Reduce context and save tokens.
  </Card>

  <Card title="Data Sync" icon="arrows-rotate" href="/optimize/data-sync">
    Reduce latency and enable semantic search.
  </Card>

  <Card title="Defender" icon="shield-halved" href="/secure/defender">
    Block prompt injections before they reach your agent.
  </Card>
</CardGroup>