--- title: "Connect LiveAgent to Softwium - APIANT.ai" description: "When \"New conversation\" fires in LiveAgent, your agent runs \"Add book\" in Softwium." canonical: "https://apiant.ai/connect/liveagent-to-softwium" --- # Connect LiveAgent to Softwium When **New conversation** fires in [LiveAgent](https://apiant.ai/connections/liveagent), your agent runs **Add book** in [Softwium](https://apiant.ai/connections/softwium). Describe the whole flow and it is built, tested on every scenario and kept running. LiveAgent **3** triggers LiveAgent **7** actions Softwium **20** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want LiveAgent and Softwium 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 LiveAgent can start in Softwium - When **New conversation** in LiveAgent then **Add book** in Softwium - When **New Customer** in LiveAgent then **Add currency** in Softwium 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 LiveAgent and Softwium ## Triggers and actions 3 triggers · 27 actions - Trigger **New conversation** Triggers when a new conversation (ticket, chat, call or message) is created in LiveAgent. - Trigger **New Customer** Triggers when a new customer (contact) is added in LiveAgent. - Trigger **New Customer (Experimental)** Triggers when a new customer (contact) is added in LiveAgent. - Action **Add customer group** Creates a new customer group in LiveAgent with a name and optional text and background colors. - Action **Add tag** Creates a new tag in LiveAgent that can be assigned to conversations. - Action **Get conversation** Returns a LiveAgent conversation (ticket) by its ID, code or public URL code, including status, owner, tags and custom field values. - Action **List conversation messages** Returns all message groups and their messages for a LiveAgent conversation, optionally limited to a date range. - Action **List conversations** Returns conversations (tickets, chats, calls) in LiveAgent, optionally filtered by owner, department, agent, status, channel, subject and dates. - Action **List customer groups** Returns every customer group defined in the LiveAgent account, with each group's id and name. - Action **List tags** Returns every tag defined in the LiveAgent account, with each tag's id and name. - Action **Add book** creates a new fake book, returns HTTP 201. Note: the vendor does not actually persist writes (test/mock API). - Action **Add currency** creates a new fake currency, returns HTTP 201. Note: the vendor does not actually persist writes (test/mock API). - Action **Add people** creates a new fake person record, returns HTTP 201. Note: the vendor does not actually persist writes (test/mock API). - Action **Add pokemon** creates a new fake pokemon, returns HTTP 201. Note: the vendor does not actually persist writes (test/mock API). - Action **Delete book** deletes the fake book with the given ID. Note: the vendor does not actually persist writes (test/mock API). - Action **Delete currency** deletes the fake currency with the given ID. Note: the vendor does not actually persist writes (test/mock API). - Action **Delete people** deletes the fake person record with the given ID. Note: the vendor does not actually persist writes (test/mock API). - Action **Delete pokemon** deletes the fake pokemon with the given ID. Note: the vendor does not actually persist writes (test/mock API). - Action **Get book** returns the fake book with the given ID, or HTTP 404 if not found. - Action **Get currency** returns the fake currency with the given ID, or HTTP 404 if not found. - Action **Get people** returns the fake person record with the given ID, or HTTP 404 if not found. - Action **Get pokemon** returns the fake pokemon with the given ID, or HTTP 404 if not found. - Action **List books** returns all fake books (optional ?limit=N query param to cap the count). Read-only test data, no auth. - Action **List currencies** returns all fake currencies (optional ?limit=N query param to cap the count). Read-only test data, no auth. - Action **List peoples** returns all fake people records (optional ?limit=N query param to cap the count). Read-only test data, no auth. - Action **List pokemons** returns all fake pokemon records (optional ?limit=N query param to cap the count). Read-only test data, no auth. - Action **Update book** partially updates the fake book with the given ID. Note: the vendor does not actually persist writes (test/mock API). - Action **Update currency** partially updates the fake currency with the given ID. Note: the vendor does not actually persist writes (test/mock API). - Action **Update people** partially updates the fake person record with the given ID. Note: the vendor does not actually persist writes (test/mock API). - Action **Update pokemon** partially updates the fake pokemon with the given ID. Note: the vendor does not actually persist writes (test/mock API). ## Each app on its own - [ **LiveAgent** LiveAgent is the only customer support app you will ever need.](https://apiant.ai/connections/liveagent) - [ **Softwium** Test data for testing and prototyping](https://apiant.ai/connections/softwium) Reviews ## What our customers say ## More from LiveAgent - [ **LiveAgent to World News Api** REST API for searching global news articles with entity extraction, sentiment analysis, and geolocation...](https://apiant.ai/connect/liveagent-to-world-news-api) - [ **LiveAgent to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/liveagent-to-salesforce) - [ **LiveAgent to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/liveagent-to-slack) - [ **LiveAgent to Mailchimp** Mailchimp marketing automation and email platform.](https://apiant.ai/connect/liveagent-to-mailchimp) - [ **LiveAgent to Stripe** Stripe is a payment processing platform for online businesses.](https://apiant.ai/connect/liveagent-to-stripe) - [ **LiveAgent to Shopify** Shopify is a commerce platform for online stores and retail point-of-sale.](https://apiant.ai/connect/liveagent-to-shopify) ## More into Softwium - [ **HubSpot to Softwium** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-softwium) - [ **Salesforce to Softwium** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-softwium) - [ **Slack to Softwium** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-softwium) - [ **Google Sheets to Softwium** Google Sheets](https://apiant.ai/connect/google-sheets-to-softwium) - [ **Gmail to Softwium** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-softwium) - [ **Google Calendar to Softwium** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-softwium) Questions ## LiveAgent and Softwium, answered ### ### What can start an automation from LiveAgent? Any of LiveAgent's 3 triggers in the catalog, including New conversation, New Customer and New Customer (Experimental). Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Softwium when something happens in LiveAgent? Any of Softwium's 20 actions, including Update book, Update currency, Update people and Update pokemon. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Softwium to LiveAgent? Softwium has no triggers in the catalog today, so automations start in LiveAgent. If you need the other direction, ask: your agent reads Softwium's API documentation and adds it. ### ### Do I have to build a connector for LiveAgent or Softwium? 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 LiveAgent and Softwium 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.