Integration
Connect Tars to Sift Science
When New Call fires in Tars, your agent runs Apply Order Decision in Sift Science. 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 Tars and Sift Science 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 Tars can start in Sift Science
When New Call in Tars
then Apply Order Decision in Sift Science
When New Contact in Tars
then Get Order Decisions in Sift Science
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 Tars and Sift Science
Triggers and actions 2 triggers · 27 actions
Trigger
New CallTriggers when a new voice call is registered in Tars.
Trigger
New ContactTriggers when a new contact is added in Tars.
Action
Create ContactCreates a Tars contact. The contact needs an email or a phone number.
Action
Delete Call ContentDeletes a Tars call's content (transcript, recordings and variables).
Action
Delete ContactDeletes a Tars contact.
Action
Get AgentReturns one Tars agent with its kind, status and published version.
Action
Get Call ConcurrencyReturns how many Tars calls are running now against your concurrency limit.
Action
Get ContactReturns one Tars contact by its ID, with name, email, phone, tags and origin.
Action
List AgentsReturns your Tars chat and voice agents.
Action
List CallsReturns Tars voice calls, newest first, optionally for one agent.
Action
List ContactsReturns Tars contacts, optionally filtered by tag or origin.
Action
List Phone NumbersReturns the phone numbers in your Tars organization.
Action
Send Campaign MessageSends a Tars campaign message (e.g. a WhatsApp template) to one phone number.
Action
Start ConversationStarts a conversation with a user through a Tars chat agent's trigger, e.g. a WhatsApp message.
Action
Update ContactUpdates a Tars contact's name, email, phone or tags. Send at least one.
Action
Validate Campaign MessageChecks a Tars campaign message for a recipient and returns its quoted price, without sending it.
Action
Apply Content DecisionApplies one of your Sift decisions to a piece of user-generated content, such as a listing or message.
Action
Apply Order DecisionApplies one of your Sift decisions, such as block or accept, to an order.
Action
Apply Session DecisionApplies one of your Sift decisions to a user's login session, for example to flag an account takeover.
Action
Apply User DecisionApplies one of your Sift decisions, such as block or accept, to a user.
Action
Get Content DecisionsReturns the latest decision applied to a piece of user-generated content for each abuse type.
Action
Get Order DecisionsReturns the latest decision applied to an order for each abuse type.
Action
Get Session DecisionsReturns the latest decision applied to a user's login session for each abuse type.
Action
Get User DecisionsReturns the latest decision applied to a user for each abuse type.
Action
Get User ScoreReturns a user's latest Sift fraud scores per abuse type, with the reasons behind each score.
Action
Get Workflow Run StatusReturns the state of a Sift workflow run, including the entity it ran on and the decisions it applied.
Action
List DecisionsLists the decisions configured in your Sift account, such as block or accept decisions, optionally filtered by abuse type or entity type.
Action
Rescore UserAsks Sift to recompute a user's fraud scores now and returns the fresh scores with their reasons.
Action
Unlabel UserRemoves the fraud label from a user in Sift, optionally for one abuse type only.
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 Tars
Tars to TrelloTrello is a visual collaboration tool that organizes projects into boards, lists, and cards.
Tars to ZoomZoom unifies cloud video conferencing, simple online meetings, group messaging, and a software-based...
Tars to TwilioCloud communications platform for sending SMS/MMS messages, making and managing voice calls, and looking up...
Tars to TypeformBuild and publish online forms, surveys, and quizzes with Typeform.
Tars to WebflowWebflow is a professional website builder and CMS for designing, building, and launching responsive...
Tars to WixThe Wix website builder gives businesses of any size the tools to create, manage and grow a fully integrated...
More into Sift Science
HubSpot to Sift ScienceHubSpot is your all-in-one stop for all of your marketing software needs.
Salesforce to Sift ScienceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Slack to Sift ScienceSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Google Sheets to Sift ScienceGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Gmail to Sift ScienceGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to Sift ScienceGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Questions
Tars and Sift Science, answered
What can start an automation from Tars?
Any of Tars's 2 triggers in the catalog, including New Call and New Contact. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Sift Science when something happens in Tars?
Any of Sift Science's 13 actions, including Apply Content Decision, Apply Order Decision, Apply Session Decision and Apply User Decision. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Sift Science to Tars?
Sift Science has no triggers in the catalog today, so automations start in Tars. If you need the other direction, ask: your agent reads Sift Science's API documentation and adds it.
Do I have to build a connector for Tars or Sift Science?
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 Tars and Sift Science 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.