Connect OneLi to ChatGPT

Add OneLi as a connector, sign in, and ask for Hebrew phone calls right from the chat.

In ChatGPT you add OneLi as a custom Plugin (a remote MCP server). Developer mode is not needed. You connect by signing in to OneLi (OAuth), because ChatGPT does not send a static API key.

The OneLi MCP address

https://mcp.oneli.io/mcp

Connect step by step

1/5

Who can use it

Available in ChatGPT on the web, on Business and Enterprise/Edu plans. On Business only admins and owners create and publish; on Enterprise/Edu also members with the Create plugins with MCPs permission. On Pro, custom servers are read-only, so they cannot place calls.

Use it in chat

In a new chat, type @ and choose OneLi, then ask: “Call the salon and book me a haircut for Thursday after 5 pm.” ChatGPT asks you to confirm before an action that starts a call.

Build your own voice agent from the chat

Besides calls for you, the chat (Claude, ChatGPT, Grok or any MCP client) can build and manage your own voice agents, the same agents you build in the agent studio: create one from a template, show all its settings, change any of them, test it in a text conversation, and put it live or pause it. Every change shows up in the studio at once, and the other way round.

Create an agent

Describe the business and what the agent should do. The chat asks what is missing, creates the agent as a draft and shows all its settings:

In the chat

Create a voice agent for Danny's Pizza in Tel Aviv that answers incoming calls:
- Goal: take a complete order (what, how many, address and time)
- Opening: "Hi, you've reached Danny's Pizza! What would you like to order?"
- Menu: Margherita ₪49, Mushroom ₪55, delivery ₪15
- A male voice, short answers, and a Supervisor that checks prices against the menu

See every setting

Ask: “Show me all the settings of the pizza agent”. get_voice_agent returns everything, grouped like the studio’s pages: the agent (direction, goal, context, language, tone), opening, the conversation steps with the situations in each, the Supervisor, sections and rules, knowledge, tools and webhooks, variables, voice and brain, and call settings (time limits, turn-taking, hearing, memory and recording), plus what still blocks going live.

Change settings

Ask in words, for example “Add a step that asks for the address and time”, “Switch to a female voice and cap calls at 5 minutes” or “Make the agent speak English”. The chat reads the agent and sends update_voice_agent only what changes. Lists (steps, knowledge, rules) replace the whole list, so it also sends what stays, with its ids. It looks like this:

MCP

update_voice_agent {
  "agent_id": "va_…",
  "steps": [
    { "id": "st_…", "name": "Opening" },
    { "name": "The order", "ask": "What would you like to order?", "knowledge": ["Menu"],
      "situations": [{ "when": "They ask for something not on the menu", "do": "Say politely we don't have it and suggest something from the menu." }] },
    { "name": "Wrap-up", "say": "Thanks, your order is on its way!" }
  ],
  "supervisor": { "enabled": true, "instructions": "Make sure every price she says is from the menu.", "knowledge": ["Menu"] },
  "limits": { "max_s": 300, "wrap_at_s": 240 }
}

Test and go live

“Test the agent: call as a customer who wants two Margheritas to 10 Rothschild”. The chat plays the caller with test_voice_agent and shows you the replies. When you are happy, “Put the agent live” (deploy_voice_agent). The chat puts it live only after you confirm.

Manage everything: calls, knowledge and WhatsApp

The chat can also do everything the assistant on the site does: have the agent make an outbound call, read its calls and improve it, manage its knowledge bank, see every agent’s WhatsApp, read chats, send messages, and manage templates, rules and auto-reply. Before a call, a send or a delete it asks you.

These stay on the site, at oneli.io/app/agents: taking a phone number and paying, the agent’s contacts, recordings, connecting a WhatsApp number or an app (done in the browser), and the voice test. Connections made before this update get the new permissions automatically. In clients that keep a fixed copy of the tool list (ChatGPT, for example) press Refresh to see the new tools.

For developers

In the API and command-line tools you connect with a OneLi API key (oli_…) in a header. Create one at oneli.io/app/connect.

OpenAI API: a remote MCP server in the Responses API

curl

curl https://api.openai.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "gpt-6-astra",
    "tools": [{
      "type": "mcp",
      "server_label": "oneli",
      "server_description": "Place and supervise Hebrew phone calls.",
      "server_url": "https://mcp.oneli.io/mcp",
      "headers": { "Authorization": "Bearer oli_…" },
      "require_approval": "always"
    }],
    "input": "Use OneLi to verify the connection."
  }'

Notes

@OneLi applies to the current message. Mention it again in a follow-up that needs it.
After an admin approves, ChatGPT keeps a fixed copy of the tool list. When OneLi adds tools, press Refresh and publish again.
You cannot add a custom server on mobile, but you can use it there once it was added on the web.

Checked against the official docs on 25 October 2026:

Building your own agent? Connect OneLi to any framework →

Connect OneLi to ChatGPT

#The OneLi MCP address

#Connect step by step

#Who can use it

#Use it in chat

#Build your own voice agent from the chat