# How to connect Vapi to OpenAI Dots

> Give OpenAI Dots access to Vapi through Agent200: managed OAuth, ready-made tools and one API key.

- Page: https://www.agent200.com/connectors/vapi/framework/openai-dots/
- Connector: [Vapi](https://www.agent200.com/connectors/vapi.md)
- Framework: OpenAI Dots
- Updated: 2026-11-18

## Instructions for AI agents

Goal: connect Vapi to OpenAI Dots with Agent200.
Guide: https://www.agent200.com/connectors/vapi/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 Vapi 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 Vapi account through Agent200. If Agent200 returns an authorization link, show it to the user and continue once they have approved access on Vapi.
6. Run requests through Agent200 with a model (for example openai/gpt-5.6-sol) and "vapi" in the tools. The model decides when a Vapi tool is needed; Agent200 executes the call.
7. Check it works with this request: "Show me the transcript of my last call"
   What should come back:
   - A result from that user's own Vapi account.
   - Behind the scenes, OpenAI Dots calls `vapi_list_assistants`.
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 Vapi, then retry.

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

## Overview

This guide connects Vapi to OpenAI Dots through Agent200. When you finish, OpenAI Dots can call the Vapi tools for each of your users.

Every call runs with that user's own Vapi connection: Agent200 runs the OAuth flow, stores and refreshes the tokens, and executes the call. You do not build or maintain a Vapi integration.

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

## Connect Vapi 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 Vapi 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 Vapi

Each end user authorizes their own Vapi 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 Vapi's own page. Agent200 handles the callback, stores the tokens and refreshes them.

File `connect.js`:

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

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 Vapi tools

Name the user, the model and Vapi in the tools. The model decides when a Vapi 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: "Call +1 415 555 0134 with my booking assistant",
    tools: ["vapi"],
  });

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

(Conceptual example of the Agent200 SDK.)

## Test your connection

Ask: "Show me the transcript of my last call"

What should come back:

- A result from that user's own Vapi account.
- Behind the scenes, OpenAI Dots calls `vapi_list_assistants`.

If you get an authorization link instead, the user has not connected Vapi yet. Show them the link, then run the request again.

## Vapi tools OpenAI Dots can call

- **List assistants** (`vapi_list_assistants`, read): List the voice assistants in the account.
- **Get an assistant** (`vapi_get_assistant`, read): Read an assistant's settings.
- **Update an assistant** (`vapi_update_assistant`, write): Change an assistant's settings, such as its first message.
- **Create a call** (`vapi_create_call`, write): Start an outbound phone call with an assistant.
- **List calls** (`vapi_list_calls`, read): List past and active calls.
- **Get a call** (`vapi_get_call`, read): Read a call's status, transcript and summary.
- **List phone numbers** (`vapi_list_phone_numbers`, read): List the phone numbers in the account.

## 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 Vapi tools.
2. **The model picks a tool.** The model decides whether a Vapi tool is needed, and with which arguments.
3. **Agent200 runs the call.** It uses that user's own Vapi 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 Vapi account.

**Permissions at every level.** Your project settings decide what the agent may request, the end user decides what they authorize, and Vapi 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 Vapi authorization is required

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

### OpenAI Dots does not use the Vapi tools

Check that Vapi is enabled for your project in the dashboard's Connectors settings and that it is in the tools you send with the request. Naming Vapi 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 Vapi 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 Vapi 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 Vapi 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 Vapi with another framework

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

---

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