Integration
Connect Cursor to seven
When Agent Pull Request Created fires in Cursor, your agent runs Add contact in seven. Describe the whole flow and it is built, tested on every scenario and kept running.
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 Cursor and seven to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne 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.aiStart 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)Example flows
What Cursor can start in seven
When Agent Pull Request Created in Cursor
then Add contact in seven
When New Agent in Cursor
then Update contact in seven
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 seven
Triggers and actions 3 triggers · 24 actions
Trigger
Agent Pull Request CreatedTriggers when the selected Cursor cloud agent opens a new GitHub pull request.
Trigger
Agent Status EqualsTriggers when a run on the chosen Cursor agent reaches the status you select, such as Finished or Error.
Trigger
New AgentTriggered when a new Cursor cloud agent is created.
Action
Add Followup Instruction to AgentSends 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 runCancels 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 AgentPermanently deletes a Cursor cloud agent. This cannot be undone. Returns the ID of the deleted agent.
Action
Find Agent StatusLooks up a Cursor cloud agent by its ID and returns its status, name, repositories, latest run and link.
Action
Get runReturns the status, timestamps, duration, final reply and pushed branches for one run of a Cursor cloud agent.
Action
Launch AgentCreates a Cursor cloud agent and immediately starts its first run on the task you describe. Returns the new agent and its run.
Action
List agentsReturns the Cursor cloud agents for the connected user, newest first, optionally filtered by pull request URL.
Action
List artifactsReturns 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 modelsReturns the recommended Cursor models you can choose from when creating an agent, including their names, aliases, parameters and variants.
Action
List repositoriesReturns the GitHub repositories the connected Cursor user can access through Cursor's GitHub App installation.
Action
List runsReturns the runs of a Cursor cloud agent, newest first, including each run's status, duration, and final reply.
Action
Add contactCreate a contact.
Action
Delete contactDelete a contact.
Action
Get balanceRetrieve account balance.
Action
Get contactRetrieve a contact by id.
Action
Get JournalYou can use this endpoint to query the last entries of your logbooks. Each query returns a maximum of 100 entries.
Action
List Active Numberslists the account's booked inbound phone numbers. Read-only.
Action
List contactsQuery the contact list.
Action
Lookup CNAMQuery the Caller ID name for any phone number worldwide. Please note that not every phone number has an entry. Since the data is collected from various sources you could get geographical locations, company names/names or the network operator in response.
Action
Lookup HLRLooks up information regarding home location register for a given phone number.
Action
Lookup MNPLooks up information regarding mobile number portability for a given phone number.
Action
Send SMSSend a SMS to one or more specific number(s).
Action
Send VoiceConverts text to speech, calls the given number and reads it loud.
Action
Update contactUpdate a contact.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Cursor
Cursor to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Cursor to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Cursor to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Cursor to Google SheetsGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Cursor to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Cursor to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into seven
HubSpot to sevenHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to sevenSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to sevenSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to sevenGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Gmail to sevenGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to sevenGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Cursor and seven, 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 seven when something happens in Cursor?
Any of seven's 13 actions, including Send SMS, Send Voice, Update contact and Add contact. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from seven to Cursor?
seven has no triggers in the catalog today, so automations start in Cursor. If you need the other direction, ask: your agent reads seven's API documentation and adds it.
Do I have to build a connector for Cursor or seven?
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 seven 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.