---
title: "Connect Cursor to GPT-trainer - APIANT.ai"
description: "When \"Agent Pull Request Created\" fires in Cursor, your agent runs \"Add agent\" in GPT-trainer."
canonical: "https://apiant.ai/connect/cursor-to-gpt-trainer"
---

# Connect Cursor to GPT-trainer

When **Agent Pull Request Created** fires in [Cursor](https://apiant.ai/connections/cursor), your agent runs **Add agent** in [GPT-trainer](https://apiant.ai/connections/gpt-trainer). Describe the whole flow and it is built, tested on every scenario and kept running.

Cursor **3** triggers Cursor **11** actions GPT-trainer **16** actions

What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.

## What do you want Cursor and GPT-trainer to do together?

Give your AI client this address.

`https://mcp.apiant.ai`

One connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.

### Set it up in your client

### Claude Code

Run this in the directory you want to work in.

`claude mcp add --transport http -s project apiant-ai https://mcp.apiant.ai`

Start Claude Code there, approve the server, and sign in in the browser page it opens.

[Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code)

### Claude, web and desktop

Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Cursor

Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Zed

Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Codex and the ChatGPT desktop app

Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Any other MCP client

Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

Example flows

## What Cursor can start in GPT-trainer

- When **Agent Pull Request Created** in Cursor then **Add agent** in GPT-trainer
- When **New Agent** in Cursor then **Send Message** in GPT-trainer

Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.

Everything your agent can do with Cursor and GPT-trainer

## Triggers and actions 3 triggers · 27 actions

- Trigger

**Agent Pull Request Created**

Triggers when the selected Cursor cloud agent opens a new GitHub pull request.

- Trigger

**Agent Status Equals**

Triggers when a run on the chosen Cursor agent reaches the status you select, such as Finished or Error.

- Trigger

**New Agent**

Triggered when a new Cursor cloud agent is created.

- Action

**Add Followup Instruction to Agent**

Sends a follow-up instruction to an existing Cursor cloud agent, either starting a new run or steering the run in progress. Returns the new run or how the steer was delivered.

- Action

**Cancel run**

Cancels the active run of a Cursor cloud agent. The run ends in the Cancelled state; start a new run to continue the conversation.

- Action

**Delete Agent**

Permanently deletes a Cursor cloud agent. This cannot be undone. Returns the ID of the deleted agent.

- Action

**Find Agent Status**

Looks up a Cursor cloud agent by its ID and returns its status, name, repositories, latest run and link.

- Action

**Get run**

Returns the status, timestamps, duration, final reply and pushed branches for one run of a Cursor cloud agent.

- Action

**Launch Agent**

Creates a Cursor cloud agent and immediately starts its first run on the task you describe. Returns the new agent and its run.

- Action

**List agents**

Returns the Cursor cloud agents for the connected user, newest first, optionally filtered by pull request URL.

- Action

**List artifacts**

Returns the files a Cursor cloud agent has produced, with each file's path, size and last modified time. Returns at most 100 artifacts.

- Action

**List models**

Returns the recommended Cursor models you can choose from when creating an agent, including their names, aliases, parameters and variants.

- Action

**List repositories**

Returns the GitHub repositories the connected Cursor user can access through Cursor's GitHub App installation.

- Action

**List runs**

Returns the runs of a Cursor cloud agent, newest first, including each run's status, duration, and final reply.

- Action

**Add agent**

Create an agent for a chatbot specified by chatbot uuid.

- Action

**Add chatbot**

Create a chatbot for the authenticated user.

- Action

**Add file data source**

Upload a file as a data source for a chatbot specified by chatbot uuid.

- Action

**Add session**

Create a chat session for a chatbot specified by chatbot uuid.

- Action

**Add URL data source**

Create a URL source for a chatbot specified by chatbot uuid.

- Action

**Delete chatbot**

Delete a single chatbot by uuid.

- Action

**Delete data source**

Delete a single data source by uuid.

- Action

**Get chatbot**

Fetch a single chatbot by uuid.

- Action

**Get session**

Fetch a single chatbot session by session uuid.

- Action

**List agents**

Fetch the list of agents for a chatbot specified by chatbot uuid.

- Action

**List chatbots**

Fetch the list of chatbots for the current user.

- Action

**List data sources**

Fetch the list of data sources for a chatbot specified by chatbot uuid.

- Action

**List messages**

Fetch the list of messages for a session specified by session uuid.

- Action

**List sessions**

Fetch the list of sessions for a chatbot specified by chatbot uuid.

- Action

**Send Message**

Send message to chatbot and receive an answer

- Action

**Update chatbot**

Update chatbot meta based on chatbot uuid.

## Each app on its own

- [ **Cursor** Cursor is an AI-powered code editor that understands your codebase, supports natural-language coding...](https://apiant.ai/connections/cursor)
- [ **GPT-trainer** GPT-trainer allows you to train a no-code ChatGPT-like chatbot using your own data and embed it onto your...](https://apiant.ai/connections/gpt-trainer)

Reviews

## What our customers say

## More from Cursor

- [ **Cursor to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/cursor-to-hubspot)
- [ **Cursor to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/cursor-to-salesforce)
- [ **Cursor to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/cursor-to-slack)
- [ **Cursor to Google Sheets** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/cursor-to-google-sheets)
- [ **Cursor to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/cursor-to-gmail)
- [ **Cursor to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/cursor-to-google-calendar)

## More into GPT-trainer

- [ **Peerdom to GPT-trainer** Peerdom helps teams navigate change with smart org charts that boost collaboration and performance.](https://apiant.ai/connect/peerdom-to-gpt-trainer)
- [ **HubSpot to GPT-trainer** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-gpt-trainer)
- [ **Salesforce to GPT-trainer** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-gpt-trainer)
- [ **Slack to GPT-trainer** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-gpt-trainer)
- [ **Google Sheets to GPT-trainer** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-gpt-trainer)
- [ **Gmail to GPT-trainer** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-gpt-trainer)

Questions

## Cursor and GPT-trainer, answered

###

### What can start an automation from Cursor?

Any of Cursor's 3 triggers in the catalog, including Agent Pull Request Created, New Agent and Agent Status Equals. Describe the moment in plain language and your agent picks the right one.

###

### What can your agent do in GPT-trainer when something happens in Cursor?

Any of GPT-trainer's 16 actions, including Send Message, Update chatbot, Add agent and Add chatbot. Your agent maps the data both ways and tests every scenario before it ships.

###

### Can it also run from GPT-trainer to Cursor?

GPT-trainer has no triggers in the catalog today, so automations start in Cursor. If you need the other direction, ask: your agent reads GPT-trainer's API documentation and adds it.

###

### Do I have to build a connector for Cursor or GPT-trainer?

No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.

###

### Can my AI client use Cursor and GPT-trainer without building an automation?

Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.

###

### What happens when something fails?

Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.

###

### Is there a free plan?

Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.
