Integration
Connect Cantina and Hjarni
When New Finding fires in Cantina, your agent runs Add File to Note in Hjarni, or New Note in Hjarni to Add Comment to Finding in Cantina. 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 Cantina and Hjarni 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)Grok
Open grok.com/connectors, choose New Connector, then Custom, and paste the address. Grok signs you in in your browser.
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 Cantina and Hjarni can do together
From Cantina to Hjarni
When New Finding in Cantina
then Add File to Note in Hjarni
When New Finding in Cantina
then Create Note in Hjarni
From Hjarni to Cantina
When New Note in Hjarni
then Add Comment to Finding in Cantina
When New Note in Hjarni
then Add company user in Cantina
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 Cantina and Hjarni
Triggers and actions 2 triggers · 35 actions
Trigger
New FindingTriggers when a new finding is reported in any repository the user can see.
Action
Add Comment to FindingAdds a comment to a finding in a Cantina repository.
Action
Add company userCreates a new user with a name and email and adds them to a company with the chosen role.
Action
Add Label to FindingAdds an existing label to a finding.
Action
Add repository userAdds an existing user to a Cantina repository with a chosen role, optionally placing a reviewer on a team.
Action
Create FindingCreates a new finding in a Cantina repository.
Action
Delete company userRemoves a user from a Cantina company.
Action
Delete repository userRemoves a user from a Cantina repository.
Action
Get CompanyReturns one Cantina company by its ID.
Action
Get FindingReturns one finding in a Cantina repository.
Action
Get ReportReturns one Cantina security review report.
Action
Get RepositoryReturns one Cantina repository by its ID.
Action
List CompaniesReturns the Cantina companies the API key's user belongs to.
Action
List Company UsersReturns the users that belong to a Cantina company.
Action
List FindingsReturns the findings reported in a Cantina repository.
Action
List LabelsReturns the finding labels across the repositories you can access.
Action
List ReportsReturns Cantina security review reports.
Action
List RepositoriesReturns the Cantina repositories (reviews, competitions and bounties) the user can see.
Action
List repository usersReturns the users of a repository (reviewers, judges and triagers), optionally filtered by name, role or comment activity.
Action
Update companyUpdates a company's profile details such as name, about text, legal information, website, social links and domain settings.
Action
Update FindingUpdates a finding's title, description, status, severity or note.
Action
Update repositoryUpdates a Cantina repository's settings, such as its name, status, kind, timeframe, reward pots, severities, labels and access options.
Trigger
New NoteTriggers when a new note is created.
Action
Add File to NoteAttaches a file to an existing note from a URL.
Action
Add tagCreate a tag.
Action
Create FolderCreates a new folder with a name, parent folder, description, and AI instructions.
Action
Create NoteCreates a new note with a title, body, tags, and folder.
Action
Delete folderDelete a container.
Action
Delete noteDelete a note (moves to trash).
Action
Delete tagDelete a tag.
Action
Get folderFetch one container by id.
Action
Get noteFetch one note by id with body, tags, container, files.
Action
List notesList notes, filter by scope/container_id/tag, paginated.
Action
List tagsList tags.
Action
Update folderUpdate a container.
Action
Update noteUpdate note fields (title, body, tags, container, append_body etc, expected_lock_version).
Action
Update tagRename/update a tag.
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 Cantina
Cantina to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Cantina to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Cantina to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Cantina to Google SheetsGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Cantina to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Cantina to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
More into Hjarni
Google Sheets to HjarniGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Gmail to HjarniGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to HjarniGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Google Drive to HjarniGoogle Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...
ActiveCampaign to HjarniActiveCampaign is a marketing automation, email marketing, and CRM platform.
Airtable to HjarniOrganize anything with Airtable, a modern database created for everyone.
Questions
Cantina and Hjarni, answered
What can start an automation from Cantina?
Any of Cantina's 1 trigger in the catalog, including New Finding. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Hjarni when something happens in Cantina?
Any of Hjarni's 14 actions, including Create Folder, Create Note, Update folder and Update note. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Hjarni to Cantina?
Yes. When something happens in Hjarni, your agent can act in Cantina too. This page covers both directions: Hjarni's triggers and Cantina's actions are listed here as well.
Do I have to build a connector for Cantina or Hjarni?
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 Cantina and Hjarni 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.