---
title: "Connect Cursor to Tavily - APIANT.ai"
description: "When \"Agent Pull Request Created\" fires in Cursor, your agent runs \"Create research task\" in Tavily."
canonical: "https://apiant.ai/connect/cursor-to-tavily"
---

# Connect Cursor to Tavily

When **Agent Pull Request Created** fires in [Cursor](https://apiant.ai/connections/cursor), your agent runs **Create research task** in [Tavily](https://apiant.ai/connections/tavily). Describe the whole flow and it is built, tested on every scenario and kept running.

Cursor **3** triggers Cursor **11** actions Tavily **7** 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 Tavily 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 Tavily

- When **Agent Pull Request Created** in Cursor then **Create research task** in Tavily
- When **New Agent** in Cursor then **Get research task status** in Tavily

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 Tavily

## Triggers and actions 3 triggers · 18 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

**Crawl**

Crawls a website starting from one address and returns the content of the pages it finds.

- Action

**Create research task**

Starts a Tavily research task for a question you supply and returns its ID and status. Use the ID with Get research task status to collect the finished report.

- Action

**Extract**

Reads one or more web pages and returns their content as markdown or plain text, plus any addresses that could not be read.

- Action

**Get research task status**

Checks a Tavily research task by its ID and returns its current status, and the finished report with its sources once the task is complete.

- Action

**Get usage**

Returns how many Tavily credits have been used this billing cycle, for both the API key and the account, along with the plan limits and a breakdown per feature.

- Action

**Map**

Maps a website starting from an address you supply and returns the list of pages found, without pulling their content.

- Action

**Search**

Searches the web for a query you supply and returns ranked results with titles, addresses and snippets, plus an optional written answer.

## 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)
- [ **Tavily** Tavily AI is a web research tool optimized for LLMs and RAG, offering access to real-time, reliable online...](https://apiant.ai/connections/tavily)

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 Tavily

- [ **CRUSH to Tavily** CRUSH is an AI powered second brain helping you collect a thought, organize it and take action.](https://apiant.ai/connect/crush-to-tavily)
- [ **HubSpot to Tavily** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-tavily)
- [ **Salesforce to Tavily** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-tavily)
- [ **Slack to Tavily** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-tavily)
- [ **Google Sheets to Tavily** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-tavily)
- [ **Gmail to Tavily** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-tavily)

Questions

## Cursor and Tavily, 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 Tavily when something happens in Cursor?

Any of Tavily's 7 actions, including Create research task, Crawl, Extract and Get research task status. Your agent maps the data both ways and tests every scenario before it ships.

###

### Can it also run from Tavily to Cursor?

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

###

### Do I have to build a connector for Cursor or Tavily?

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 Tavily 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.
