Integration
Connect Cantina and Vast.ai
When New Finding fires in Cantina, your agent runs Get Current User in Vast.ai, or New Matching Offer in Vast.ai 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 Vast.ai 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 Vast.ai can do together
From Cantina to Vast.ai
When New Finding in Cantina
then Get Current User in Vast.ai
When New Finding in Cantina
then Search Benchmarks in Vast.ai
From Vast.ai to Cantina
When New Matching Offer in Vast.ai
then Add Comment to Finding in Cantina
When New Matching Offer in Vast.ai
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 Vast.ai
Triggers and actions 2 triggers · 25 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 Matching OfferTriggers when a new GPU machine offer appears on the Vast.ai marketplace that matches your filters (GPU model, price, reliability, location and more).
Action
Get Current UserReturns the profile of the Vast.ai user the connected API key belongs to, including email and account balance.
Action
Search BenchmarksReturns Vast.ai benchmark results matching a search query, such as machines scoring above a threshold.
Action
Search OffersSearches available Vast.ai GPU machine offers, filtered by GPU model, count, price, reliability, location and other hardware specs, and returns the matching offers.
Action
Search TemplatesSearches your own and publicly shared Vast.ai templates matching filter conditions, returning the matching templates.
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 Vast.ai
HubSpot to Vast.aiHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to Vast.aiSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to Vast.aiSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to Vast.aiGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Gmail to Vast.aiGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to Vast.aiGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Cantina and Vast.ai, 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 Vast.ai when something happens in Cantina?
Any of Vast.ai's 4 actions, including Get Current User, Search Benchmarks, Search Offers and Search Templates. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Vast.ai to Cantina?
Yes. When something happens in Vast.ai, your agent can act in Cantina too. This page covers both directions: Vast.ai's triggers and Cantina's actions are listed here as well.
Do I have to build a connector for Cantina or Vast.ai?
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 Vast.ai 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.