# Connect Twilio to OpenAI Dots with OpenAI models and the Agent200 SDK

> Dots cannot send an API key to a custom MCP server, so this guide builds an always-on Twilio agent with OpenAI's models and the Agent200 SDK.

- Page: https://www.agent200.com/tools/twilio/framework/openai-dots/
- Connector: [Twilio](https://www.agent200.com/tools/twilio.md)
- Framework: OpenAI Dots
- Updated: 2026-11-15

## Instructions for AI agents

Goal: connect Twilio to OpenAI Dots with Agent200.
Guide: https://www.agent200.com/tools/twilio/framework/openai-dots/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Make sure Twilio is enabled for the project in the Agent200 dashboard (Connectors), with the endpoints and scopes the task needs.
3. Add the Agent200 SDK to the project and create a client with that key.
4. Give every request a stable id for the end user. Agent200 uses only that user's own connections.
5. Connect the user's Twilio account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on Twilio.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "twilio" in the tools. The model decides when a Twilio tool is needed; Agent200 executes the call.
7. Check it works with this request: "Text the on-call engineer that the deploy is done"
   What should come back:
   - An answer in `result.output`, built from the user's own Twilio data.
   - Behind the scenes, the model calls a Twilio tool, such as `twilio_list_messages`, and Agent200 runs it.
8. If a tool is missing or a call is refused, check the project's Connectors settings in the dashboard and the access the user granted in Twilio, then retry.

The code on the guide page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## Overview

OpenAI Dots use the plugins connected to a ChatGPT account, and ChatGPT's custom MCP servers cannot send an API key. To give an always-on agent the Twilio tools, build it with the Agent200 SDK and OpenAI's models: this guide shows how.

Your agent then calls the Twilio tools with each user's own Twilio connection: Agent200 runs the OAuth flow, stores the tokens and keeps them fresh.

- **Connector:** [Twilio](https://www.agent200.com/tools/twilio/)
- **Works with:** OpenAI Dots · Your own agent code
- **Authentication:** Managed OAuth, per end user
- **You need:** [An Agent200 API key](https://agent200.com/platform/apikeys/)
- **Tools:** [7 tools](https://www.agent200.com/tools/twilio/framework/openai-dots/#tools)
- **Model in examples:** `openai/gpt-5.6-sol`

## Before you start

- **An Agent200 API key.** Create one on the [API keys page](https://agent200.com/platform/apikeys/) of the dashboard.
- **Twilio enabled for your project.** In the dashboard's Connectors settings, with the endpoints and scopes your agent needs.
- **An end user with a Twilio account.** They approve access once, on Twilio's own page.
- **A model for your agent.** The examples use openai/gpt-5.6-sol, through the same Agent200 API key.

## Connect Twilio to OpenAI Dots

### Step 1: Create your Agent200 API key

Open the API keys page in the Agent200 dashboard and choose Create an API key. Copy the key and store it as an environment variable, AGENT200_API_KEY, or in your secrets manager. One key covers Twilio and every other connector and model enabled for your project. Keep it out of chats, prompts and source control.

Create an API key: https://agent200.com/platform/apikeys/

File `.env`:

```bash
# Keep the key out of your code, prompts and chats.
export AGENT200_API_KEY="paste-your-key-here"
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Set up the Agent200 SDK

Add the SDK to your project and create a client with the key from the environment.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Let your user connect Twilio

Each end user authorizes their own Twilio account once, through managed OAuth. If the user has not connected yet, Agent200 returns an authorization link: show it to them, and they approve access on Twilio's own page. Agent200 handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Twilio account, once.
const connection = await agent200
  .user("user_123")
  .connect("twilio");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 4: Run with the Twilio tools

Name the user, the model and Twilio in the tools. The model decides when a Twilio tool is needed, and Agent200 executes the call with the user's own connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Text the on-call engineer that the deploy is done",
    tools: ["twilio"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Test your connection

Ask: "Text the on-call engineer that the deploy is done"

What should come back:

- An answer in `result.output`, built from the user's own Twilio data.
- Behind the scenes, the model calls a Twilio tool, such as `twilio_list_messages`, and Agent200 runs it.

If Agent200 returns an authorization link instead, the user has not connected Twilio yet. Go back to the connect step.

## Twilio tools OpenAI Dots can call

- **Send an SMS** (`twilio_send_sms`, write): Send a text or MMS message from one of the account's numbers.
- **List messages** (`twilio_list_messages`, read): List sent and received messages, filtered by number or date.
- **Get a message** (`twilio_get_message`, read): Read a message's body and delivery status.
- **Place a call** (`twilio_make_call`, write): Start an outbound call that follows the instructions you give it.
- **List calls** (`twilio_list_calls`, read): List recent calls with their status and duration.
- **List recordings** (`twilio_list_recordings`, read): List call recordings on the account.
- **List phone numbers** (`twilio_list_phone_numbers`, read): List the phone numbers the account owns.

## How it works

1. **Your app sends the request.** It calls Agent200 with the model, instructions, the input, the end user's id and the Twilio tools.
2. **The model picks a tool.** The model decides whether a Twilio tool is needed, and with which arguments.
3. **Agent200 runs the call.** It uses that user's own Twilio connection, within the endpoints and scopes your project allows, and returns the result to the model.
4. **Your app gets the result.** Agent200 returns the completed result. Your app decides when the agent runs and what happens next.

**Each user's own connection.** Connections belong to individual end users. A request for one user never reaches another user's Twilio account.

**Permissions at every level.** Your project settings decide what the agent may request, the end user decides what they authorize, and Twilio enforces what its API grants.

## Troubleshooting

### Why not connect Agent200 to a dot directly?

A dot uses the plugins connected to your ChatGPT account, and ChatGPT’s custom MCP servers cannot send an API key. Building the agent with the Agent200 SDK, as on this page, is the route that works.

### The request says Twilio authorization is required

The end user has not connected Twilio yet, or the connection needs to be approved again. Agent200 returns an authorization link: show it to the user, let them approve access on Twilio's own page, then run the request again.

### OpenAI Dots does not use the Twilio tools

Check that Twilio is enabled for your project in the dashboard's Connectors settings and that it is in the tools you send with the request. Naming Twilio in the request, or in the instructions, also helps the model choose the right tool.

### A tool call is refused or returns less than expected

Agent200 runs only what your project allows (services, endpoints and scopes), and Twilio returns only what the end user authorized. Widen the endpoints or scopes in the dashboard if the agent needs more, then ask the user to connect Twilio again so they can approve the new access.

### The results come from the wrong account

Every request names an end user (`user_123` in the examples). Pass the id of the person your agent is working for: Agent200 then uses only that user's Twilio connection, never another user's.

### The API key was pasted into a chat or committed

Create a new key on the [API keys page](https://agent200.com/platform/apikeys/), update `AGENT200_API_KEY` wherever your app reads it, and stop using the old one. Keep keys in environment variables or a secrets manager, never in prompts, chats or source control.

## Use Twilio with another framework

- [Twilio + Claude](https://www.agent200.com/tools/twilio/framework/claude.md)
- [Twilio + ChatGPT](https://www.agent200.com/tools/twilio/framework/chatgpt.md)
- [Twilio + Claude Code](https://www.agent200.com/tools/twilio/framework/claude-code.md)
- [Twilio + Muse](https://www.agent200.com/tools/twilio/framework/muse.md)
- [Twilio + Grok Bot](https://www.agent200.com/tools/twilio/framework/grok-bot.md)
- [Twilio + Claude Duet](https://www.agent200.com/tools/twilio/framework/claude-duet.md)
- [Twilio + Hermes Agent](https://www.agent200.com/tools/twilio/framework/hermes-agent.md)
- [Twilio + OpenClaw](https://www.agent200.com/tools/twilio/framework/openclaw.md)

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
