App

Cursor integrations

Connect Cursor to any other app, or use it from your AI client over MCP. Cursor is an AI-powered code editor that understands your codebase, supports natural-language coding, multi-line edits, and background agents.

Connects with an API keycursor.com
3 triggers11 actions

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

Build solutions, not workarounds.

What do you want to automate with Cursor?

Ask the assistant

You'll sign in before anything runs. What you typed comes with you.

Connect your AI client

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)
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)
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)
Zed

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

Setup guide (opens in a new tab)
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)
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)

Popular

Cursor with the apps people pair it with most

Pair it

Connect Cursor with another app

What your agent can do with Cursor

Triggers and actions 3 triggers · 11 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.

Reviews

What our customers say

Questions

Cursor, answered

Is there a Cursor MCP server?

APIANT's MCP server at https://mcp.apiant.ai works with Cursor. Add that address to any AI client that takes a remote MCP server and sign in once in your browser. Your client can then run Cursor actions on demand, or have APIANT build, test and run automations that use Cursor. Nothing to install.

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 Cursor?

Any of Cursor's 11 actions, including Add Followup Instruction to Agent, Find Agent Status, Get run and Launch Agent. Your agent maps the data both ways and tests every scenario before it ships.

Can I use Cursor directly from Claude, ChatGPT or Cursor?

Yes. Connect your AI client to APIANT once and it works with Cursor two ways. Ask it to do something in Cursor 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 on its own. A one-off action uses your plan's tasks the same way an automation step does.

Do I need to write code against the Cursor API?

No. APIANT connects to the Cursor API for you, with your Cursor API key. Describe what you want in plain language and your agent builds it on the Cursor triggers and actions in the catalog. If you need an endpoint that is not there yet, your agent reads the Cursor API documentation and adds it.

Which apps can Cursor connect to?

Any app in the catalog; the list on this page pairs Cursor with each of them. If the other app is missing, point your agent at its API documentation and it builds the connector.

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.