# Brevo + OpenAI (ChatGPT) — Pipedream Connect

> Connect a user's Brevo and OpenAI (ChatGPT) accounts and expose tools for both apps directly in your product or your agent.

- Apps: Brevo (`brevo`) + OpenAI (ChatGPT) (`openai`)
- This page (HTML): https://pipedream.com/apps/brevo/integrations/openai
- One `external_user_id` owns both connected accounts, and each account stays independently revocable.

## One session, both toolsets (recommended)

- Endpoint: `https://remote.mcp.pipedream.net/v3`
- Headers: `Authorization: Bearer <token>` · `x-pd-project-id` · `x-pd-environment` · `x-pd-external-user-id` · `x-pd-app-slug: brevo,openai`
- `x-pd-app-slug` takes a comma-separated list, so `brevo,openai` is one session on one transport. Both toolsets arrive from a single `listTools()`, and a tool is called exactly as it would be in a single-app session.

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const accessToken = await pd.rawAccessToken

const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": process.env.PIPEDREAM_PROJECT_ID!,
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "brevo,openai",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// One list, both toolsets: Brevo and OpenAI (ChatGPT) tools arrive
// together, each keyed by its own app's slug.

// e.g. run Add or Update a contact:
const result = await mcp.callTool({
  name: "brevo-add-or-update-contact",
  arguments: {
    providedIdentifier: "Contact",
    email: "Email",
  },
})
```

Docs: [MCP guide](https://pipedream.com/docs/connect/mcp/developers.md)

## Both apps from your backend

```ts
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const externalUserId = "{external_user_id}" // any stable ID for this user in your system

const [brevoTools, openaiTools] =
  await Promise.all([
    pd.components.list({ app: "brevo" }),
    pd.components.list({ app: "openai" }),
  ])

// One external user owns both connected accounts, so either app's tools
// run on their behalf with the same externalUserId.
```

Docs: [Managed auth guide](https://pipedream.com/docs/connect/managed-auth/quickstart.md) · [Tools guide](https://pipedream.com/docs/connect/components.md)

## Brevo

- API slug: `brevo` (use in MCP headers and tool keys)
- Auth: API key (Pipedream-managed)
- Categories: CRM
- Website: https://www.brevo.com/
- App page (HTML): https://pipedream.com/apps/brevo
- Tools: 2 actions · 2 triggers

Full tool list, API proxy, and SDK quickstart: https://pipedream.com/apps/brevo.md

### Actions (2)

- [Add or Update a contact](https://pipedream.com/apps/brevo/actions/add-or-update-contact.md) — `brevo-add-or-update-contact`
- [Send Transactional Email](https://pipedream.com/apps/brevo/actions/send-transactional-email.md) — `brevo-send-transactional-email`

### Triggers (2)

- [New Marketing Webhook (Instant)](https://pipedream.com/apps/brevo/triggers/marketing-webhook.md) — `brevo-marketing-webhook`
- [New Transactional Webhook (Instant)](https://pipedream.com/apps/brevo/triggers/transactional-webhook.md) — `brevo-transactional-webhook`

## OpenAI (ChatGPT)

- API slug: `openai` (use in MCP headers and tool keys)
- Auth: API key (Pipedream-managed)
- Categories: Artificial Intelligence (AI)
- Website: https://openai.com/
- App page (HTML): https://pipedream.com/apps/openai
- Tools: 46 actions · 4 triggers

Full tool list, API proxy, and SDK quickstart: https://pipedream.com/apps/openai.md

### Actions (top 8 of 46)

- [Chat](https://pipedream.com/apps/openai/actions/chat.md) — `openai-chat`
- [Chat using Web Search](https://pipedream.com/apps/openai/actions/chat-using-web-search.md) — `openai-chat-using-web-search`
- [Chat using Functions](https://pipedream.com/apps/openai/actions/chat-using-functions.md) — `openai-chat-using-functions`
- [Chat using File Search](https://pipedream.com/apps/openai/actions/chat-using-file-search.md) — `openai-chat-using-file-search`
- [Summarize Text](https://pipedream.com/apps/openai/actions/summarize.md) — `openai-summarize`
- [Classify Items into Categories](https://pipedream.com/apps/openai/actions/classify-items-into-categories.md) — `openai-classify-items-into-categories`
- [Translate Text (Whisper)](https://pipedream.com/apps/openai/actions/translate-text.md) — `openai-translate-text`
- [Create Transcription](https://pipedream.com/apps/openai/actions/create-transcription.md) — `openai-create-transcription`

### Triggers (4)

- [New Batch Completed](https://pipedream.com/apps/openai/triggers/new-batch-completed.md) — `openai-new-batch-completed`
- [New File Created](https://pipedream.com/apps/openai/triggers/new-file-created.md) — `openai-new-file-created`
- [New Fine Tuning Job Created](https://pipedream.com/apps/openai/triggers/new-fine-tuning-job-created.md) — `openai-new-fine-tuning-job-created`
- [New Run State Changed](https://pipedream.com/apps/openai/triggers/new-run-state-changed.md) — `openai-new-run-state-changed`

---

- Brevo: https://pipedream.com/apps/brevo.md · OpenAI (ChatGPT): https://pipedream.com/apps/openai.md
- All apps: https://pipedream.com/apps — index: https://pipedream.com/llms.txt
- Pipedream docs for agents: https://pipedream.com/docs/llms.txt
