--- title: "Connect Willo to Anthropic - APIANT.ai" description: "When \"List Users\" fires in Willo, your agent runs \"Create message batch\" in Anthropic." canonical: "https://apiant.ai/connect/willo-to-anthropic" --- # Connect Willo to Anthropic When **List Users** fires in [Willo](https://apiant.ai/connections/willo), your agent runs **Create message batch** in [Anthropic](https://apiant.ai/connections/anthropic). Describe the whole flow and it is built, tested on every scenario and kept running. Willo **1** trigger Willo **19** actions Anthropic **9** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Willo and Anthropic 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 Willo can start in Anthropic - When **List Users** in Willo then **Create message batch** in Anthropic - When **List Users** in Willo then **Send model a message** in Anthropic 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 Willo and Anthropic ## Triggers and actions 1 trigger · 28 actions - Trigger **List Users** Triggers when a new user is added to your Willo account. - Action **Accept Candidate** Marks a participant in a Willo interview as Accepted and returns the updated participant. Can also update the participant's name, phone number and custom ID in the same step. - Action **Add department** Creates a new department in your Willo organisation and returns the department, including its key and branding. - Action **Add interview from template** Creates a new interview in Willo from one of your interview templates and returns the new interview. - Action **Create Company** Creates a new company as a child organisation under your Willo organisation, with the owner you name. - Action **Create Interview** Creates a new video interview in Willo with its questions, department, message templates and settings. - Action **Delete interview** Deletes an interview from your Willo account. - Action **Delete participant** Deletes a participant from Willo. Returns whether the deletion was confirmed. - Action **Get interview** Returns a Willo interview by its key, including its questions, owner, department, reviewers, message templates and settings. An error occurs if the interview is not found. - Action **Get participant** Returns a Willo participant (candidate) with their contact details, status, interview, department, scores and answers. - Action **Get user** Returns a Willo user's details, including email, full name, phone, role and status. - Action **Invite Someone** Invites a person to a Willo interview as a participant and returns the new participant with their invite link. - Action **List departments** Returns the departments in your Willo organisation, optionally filtered by name, owner email or owner. - Action **List interviews** Returns the interviews in your Willo account, optionally narrowed by department, owner or a search term, and sorted the way you choose. - Action **List message templates** Returns the message templates (email and SMS) in your Willo account, optionally filtered by title, type or trigger. - Action **List participants** Returns the participants in your Willo account, optionally narrowed to an interview, department or owner, or by a text search. - Action **List users** Returns the users in your Willo account with their key, email and full name. - Action **Reject Candidate** Rejects a candidate by setting the participant's status to Rejected, optionally updating their name, phone or custom ID. - Action **Update interview** Updates an existing interview's details, questions, reviewers, message templates and settings, changing only the values you provide. Returns the updated interview. - Action **Update participant** Updates a participant's name, phone, status (Accepted or Rejected) or your own reference ID. - Action **Anthropic agent message** Runs one AI agent turn on Anthropic and returns the model's reply. The turn is billed to the Anthropic account connected on this step, and the agent can call the account's AI tool automations. - Action **Cancel message batch** Cancel a Message Batch that is still processing. - Action **Count tokens in a message** Count the number of input tokens a Messages API request would use, without creating the message. - Action **Create message batch** Submit a batch of Messages API requests for asynchronous processing. - Action **Get message batch** Retrieve the status and request counts of a Message Batch by id. - Action **Get model** Retrieve details for a specific Claude model by id. - Action **List message batches** List Message Batches in the workspace, most recently created first. - Action **List models** List the available Claude models, most recently released first. - Action **Send model a message** Send a message to a Claude model and return its response. Supports the full Messages API: model, system prompt, multi-turn messages, max_tokens, tools, and adaptive thinking. ## Each app on its own - [ **Willo** Willo helps you get answers to your questions faster with video interviewing.](https://apiant.ai/connections/willo) - [ **Anthropic** Anthropic builds Claude, a family of large language models.](https://apiant.ai/connections/anthropic) Reviews ## What our customers say ## More from Willo - [ **Willo to Zoom** Zoom unifies cloud video conferencing, simple online meetings, group messaging, and a software-based...](https://apiant.ai/connect/willo-to-zoom) - [ **Willo 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/willo-to-wix) - [ **Willo to LinkedIn** LinkedIn is a professional networking platform enabling job seekers, companies, and thought leaders to...](https://apiant.ai/connect/willo-to-linkedin) - [ **Willo to Facebook** Facebook is a social media and advertising platform used by individuals and businesses to connect, share...](https://apiant.ai/connect/willo-to-facebook) - [ **Willo to Supabase** Supabase is an open-source backend-as-a-service providing a Postgres database, authentication, storage, and...](https://apiant.ai/connect/willo-to-supabase) - [ **Willo to ElevenLabs** ElevenLabs is an AI audio research and deployment company.](https://apiant.ai/connect/willo-to-elevenlabs) ## More into Anthropic - [ **HubSpot to Anthropic** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-anthropic) - [ **Salesforce to Anthropic** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-anthropic) - [ **Mailchimp to Anthropic** Mailchimp marketing automation and email platform.](https://apiant.ai/connect/mailchimp-to-anthropic) - [ **Stripe to Anthropic** Stripe is a payment processing platform for online businesses.](https://apiant.ai/connect/stripe-to-anthropic) - [ **Shopify to Anthropic** Shopify is a commerce platform for online stores and retail point-of-sale.](https://apiant.ai/connect/shopify-to-anthropic) - [ **QuickBooks Online to Anthropic** QuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...](https://apiant.ai/connect/quickbooks-online-to-anthropic) Questions ## Willo and Anthropic, answered ### ### What can start an automation from Willo? Any of Willo's 1 trigger in the catalog, including List Users. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Anthropic when something happens in Willo? Any of Anthropic's 9 actions, including Create message batch, Send model a message, Anthropic agent message and Count tokens in a message. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Anthropic to Willo? Anthropic has no triggers in the catalog today, so automations start in Willo. If you need the other direction, ask: your agent reads Anthropic's API documentation and adds it. ### ### Do I have to build a connector for Willo or Anthropic? 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 Willo and Anthropic 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.