--- title: "Connect CallRail to VLM Run - APIANT.ai" description: "When \"Outbound Call Completed\" fires in CallRail, your agent runs \"Add file\" in VLM Run." canonical: "https://apiant.ai/connect/callrail-to-vlm-run" --- # Connect CallRail to VLM Run When **Outbound Call Completed** fires in [CallRail](https://apiant.ai/connections/callrail), your agent runs **Add file** in [VLM Run](https://apiant.ai/connections/vlm-run). Describe the whole flow and it is built, tested on every scenario and kept running. CallRail **5** triggers VLM Run **16** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want CallRail and VLM Run 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 CallRail can start in VLM Run - When **Outbound Call Completed** in CallRail then **Add file** in VLM Run - When **SMS Received** in CallRail then **Analyze Document** in VLM Run 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 CallRail and VLM Run ## Triggers and actions 5 triggers · 16 actions - Trigger **Form Captured** Triggers when a form is captured. - Trigger **Outbound Call Completed** Triggers after an outbound phone call has been completed and its recording and transcription have been completed and attached. It contains the full data about the call. This trigger should not be expected to be real-time and has a maximum delay of 20 minutes after the hangup before it fires. - Trigger **Phone Call Started** Triggers when an inbound phone call is started. - Trigger **SMS Received** Triggers when an SMS message is received. - Trigger **SMS Sent** Triggers when an SMS message is sent. - Action **Add agent** Create an agent. - Action **Add file** Upload a file. - Action **Analyze Audio** Processes and analyzes audio content. - Action **Analyze Document** Extracts structured data from a document. - Action **Analyze Image** Generates a description from an image. - Action **Analyze Video** Processes and analyzes video content. - Action **Execute Agent** Executes a specific agent with a prompt using vlmrun. - Action **Generate chat completion** Multimodal chat completion. - Action **Get execution** Get an agent execution by ID. - Action **Get file** Get a file by ID. - Action **Get prediction** Get a prediction by ID. - Action **List agents** List agents. - Action **List executions** List agent executions. - Action **List files** List files. - Action **List models** List models. - Action **List predictions** Lists the predictions made on your VLM Run account. ## Each app on its own - [ **CallRail** CallRail is an analytics platform designed for those who rely on quality calls and inbound leads to measure...](https://apiant.ai/connections/callrail) - [ **VLM Run** VLM Run is a visual AI platform that extracts data from images, videos, and documents, streamlining...](https://apiant.ai/connections/vlm-run) Reviews ## What our customers say ## More from CallRail - [ **CallRail to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/callrail-to-hubspot) - [ **CallRail to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/callrail-to-salesforce) - [ **CallRail to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/callrail-to-slack) - [ **CallRail to Google Sheets** Google Sheets](https://apiant.ai/connect/callrail-to-google-sheets) - [ **CallRail to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/callrail-to-gmail) - [ **CallRail to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/callrail-to-google-calendar) ## More into VLM Run - [ **HubSpot to VLM Run** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-vlm-run) - [ **Salesforce to VLM Run** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-vlm-run) - [ **Slack to VLM Run** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-vlm-run) - [ **Google Sheets to VLM Run** Google Sheets](https://apiant.ai/connect/google-sheets-to-vlm-run) - [ **Gmail to VLM Run** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-vlm-run) - [ **Google Calendar to VLM Run** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-vlm-run) Questions ## CallRail and VLM Run, answered ### ### What can start an automation from CallRail? Any of CallRail's 5 triggers in the catalog, including Outbound Call Completed, SMS Received, Form Captured and Phone Call Started. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in VLM Run when something happens in CallRail? Any of VLM Run's 16 actions, including Add agent, Add file, Analyze Audio and Analyze Document. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from VLM Run to CallRail? VLM Run has no triggers in the catalog today, so automations start in CallRail. If you need the other direction, ask: your agent reads VLM Run's API documentation and adds it. ### ### Do I have to build a connector for CallRail or VLM Run? 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 CallRail and VLM Run without building an automation? Yes. With your AI client connected to APIANT, ask it to do something in VLM Run 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.