--- title: "Connect Vapi to TypeSafe - APIANT.ai" description: "When \"New Assistant\" fires in Vapi, your agent runs \"Ask a Yes/No Question\" in TypeSafe." canonical: "https://apiant.ai/connect/vapi-to-typesafe" --- # Connect Vapi to TypeSafe When **New Assistant** fires in [Vapi](https://apiant.ai/connections/vapi), your agent runs **Ask a Yes/No Question** in [TypeSafe](https://apiant.ai/connections/typesafe). Describe the whole flow and it is built, tested on every scenario and kept running. Vapi **3** triggers Vapi **21** actions TypeSafe **3** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Vapi and TypeSafe to do together? 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)](https://apiant.ai/docs/mcp/claude-code) ### 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)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) ### Zed Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) Example flows ## What Vapi can start in TypeSafe - When **New Assistant** in Vapi then **Ask a Yes/No Question** in TypeSafe - When **New Call** in Vapi then **Classify Into Options** in TypeSafe 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 Vapi and TypeSafe ## Triggers and actions 3 triggers · 24 actions - Trigger **New Assistant** Triggers when a new assistant is created in your Vapi organization. - Trigger **New Call** Triggers when a new call is created in Vapi, optionally limited to one assistant or phone number. - Trigger **New File** Triggers when a new file is uploaded to your Vapi account. - Action **Add assistant** Creates a new Vapi voice assistant with its model, voice, transcriber, first message and call behavior. - Action **Add phone number** Adds a phone number to Vapi: a free Vapi number, or one you bring from Twilio, Vonage, Telnyx or your own SIP trunk. Returns the new phone number record. - Action **Add squad** Creates a squad: a group of assistants that hand a call off to one another, starting with the first member. - Action **Add tool** Creates a tool in Vapi (for example a function, end-call, transfer-call or API-request tool) that assistants can use during calls. - Action **Create Call** Starts a Vapi call (or a batch of outbound calls) using a saved or one-off assistant, squad or workflow, and returns the created call. - Action **Create Chat** Sends a message to a Vapi assistant or squad as a text chat and returns the chat, including the assistant's reply messages. - Action **Delete assistant** Deletes an assistant from your Vapi account and returns the deleted assistant. - Action **Delete Call Data** Deletes a call and its data, including recordings, and returns the deleted call. - Action **Delete Chat** Deletes a chat from your Vapi account and returns the deleted chat's details. - Action **Delete File** Deletes a file from your Vapi account. - Action **Find Call** Finds calls matching a call id, assistant, phone number, or created/updated date range. Returns up to 1000 matching calls. - Action **Get assistant** Returns a Vapi assistant's full configuration, including its model, voice, transcriber and first message. - Action **Get file** Returns a file uploaded to Vapi, including its name, size, type, processing status and download URL. - Action **List assistants** Returns the voice assistants in your Vapi account, optionally filtered by when they were created or last updated. - Action **List chats** Returns the chats in your Vapi account, optionally filtered by assistant, squad, session or creation/update date. - Action **List files** Returns the files uploaded to your Vapi account, optionally filtered by purpose. - Action **List phone numbers** Returns the phone numbers in your Vapi account, optionally filtered by when they were created or updated. - Action **List tools** Returns the tools configured in your Vapi account, optionally filtered by when they were created or updated. - Action **Update Call** Updates the name of an existing Vapi call. - Action **Update phone number** Updates a Vapi phone number's name, the assistant, squad or workflow that answers it, and its provider settings. - Action **Upload File** Uploads a file to Vapi, for use by assistants or knowledge bases, and returns the stored file record. - Action **Ask a Yes/No Question** Asks a yes/no question about a piece of content and returns how likely the answer is yes, as a number from 0 to 1. Use it to check a condition that needs judgement rather than an exact match, such as whether a message sounds urgent or whether a review is a complaint. - Action **Classify Into Options** Sorts a piece of content into one of the options you define and tells you how certain the choice is. Use it to route a ticket to a team, tag an enquiry by intent, or pick a category, and branch on the confidence so unclear cases go to a person instead. - Action **Score Against Levels** Rates a piece of content against levels you describe, from lowest to highest, and tells you how certain the rating is. Use it to grade severity, sentiment, lead quality or risk on a scale of your own wording rather than a yes/no answer. ## Each app on its own - [ **Vapi** Vapi is a developer-first Voice AI platform for building natural, low-latency, multilingual phone agents via...](https://apiant.ai/connections/vapi) - [ **TypeSafe** TypeSafe's Jev model answers typed questions about a piece of content and tells you how certain it is.](https://apiant.ai/connections/typesafe) Reviews ## What our customers say ## More from Vapi - [ **Vapi to Zoom** Zoom unifies cloud video conferencing, simple online meetings, group messaging, and a software-based...](https://apiant.ai/connect/vapi-to-zoom) - [ **Vapi to Webflow** Webflow is a professional website builder and CMS for designing, building, and launching responsive...](https://apiant.ai/connect/vapi-to-webflow) - [ **Vapi to Wix** The Wix website builder gives businesses of any size the tools to create, manage and grow a fully integrated...](https://apiant.ai/connect/vapi-to-wix) - [ **Vapi to LinkedIn** LinkedIn is a professional networking platform enabling job seekers, companies, and thought leaders to...](https://apiant.ai/connect/vapi-to-linkedin) - [ **Vapi to Facebook** Facebook is a social media and advertising platform used by individuals and businesses to connect, share...](https://apiant.ai/connect/vapi-to-facebook) - [ **Vapi to Anthropic** Anthropic builds Claude, a family of large language models.](https://apiant.ai/connect/vapi-to-anthropic) ## More into TypeSafe - [ **HubSpot to TypeSafe** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-typesafe) - [ **Salesforce to TypeSafe** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-typesafe) - [ **Slack to TypeSafe** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-typesafe) - [ **Google Sheets to TypeSafe** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-typesafe) - [ **Gmail to TypeSafe** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-typesafe) - [ **Google Drive to TypeSafe** Google Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...](https://apiant.ai/connect/google-drive-to-typesafe) Questions ## Vapi and TypeSafe, answered ### ### What can start an automation from Vapi? Any of Vapi's 3 triggers in the catalog, including New Assistant, New Call and New File. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in TypeSafe when something happens in Vapi? Any of TypeSafe's 3 actions, including Ask a Yes/No Question, Classify Into Options and Score Against Levels. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from TypeSafe to Vapi? TypeSafe has no triggers in the catalog today, so automations start in Vapi. If you need the other direction, ask: your agent reads TypeSafe's API documentation and adds it. ### ### Do I have to build a connector for Vapi or TypeSafe? 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 Vapi and TypeSafe 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.