--- title: "Connect Clientary to Nano Nets - APIANT.ai" description: "When \"New Expense\" fires in Clientary, your agent runs \"Extract data from file\" in Nano Nets." canonical: "https://apiant.ai/connect/clientary-to-nano-nets" --- # Connect Clientary to Nano Nets When **New Expense** fires in [Clientary](https://apiant.ai/connections/clientary), your agent runs **Extract data from file** in [Nano Nets](https://apiant.ai/connections/nano-nets). Describe the whole flow and it is built, tested on every scenario and kept running. Clientary **3** triggers Clientary **14** actions Nano Nets **8** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Clientary and Nano Nets 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 Clientary can start in Nano Nets - When **New Expense** in Clientary then **Extract data from file** in Nano Nets - When **New Invoice** in Clientary then **Extract data from file asynchronously** in Nano Nets 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 Clientary and Nano Nets ## Triggers and actions 3 triggers · 22 actions - Trigger **New Expense** Triggers when a new expense is recorded in your Clientary account during the current fiscal year. - Trigger **New Invoice** Triggers when a new invoice is created in Clientary, optionally limited to invoices in a given status or matching a search. - Trigger **New Staff** Triggers when a new staff user is added to your Clientary account. - Action **Add comment** Posts a comment on an invoice, estimate, project, task, proposal or contract and notifies the people involved. - Action **Add contact** Creates a new contact (an individual person) under an existing Clientary client. - Action **Add contract** Creates a contract for a client in Clientary, optionally starting from a contract template, with its sections and signers. - Action **Add proposal** Creates a proposal for a client in Clientary, optionally starting from a proposal template, with its sections and signers. - Action **Add retainer** Creates a retainer for a client in Clientary: an up-front payment request kept apart from ordinary invoices. - Action **Client** Creates a new client in Clientary with its name, address, tax id, website and description. - Action **Create Estimate** Creates an estimate in Clientary, optionally for a client, with its dates, taxes, notes and line items. - Action **Create Invoice** Creates an invoice in Clientary, optionally for a client, with dates, currency, taxes, notes and line items. - Action **Create Lead** Creates a new lead (a prospective client) in Clientary. - Action **Create Task** Creates a new task (a to-do item) in Clientary, optionally on a project and assigned to a staff member. - Action **Expense** Creates a new expense in Clientary, optionally assigned to a client or project. - Action **Get client** Returns a single Clientary client by its ID, including its contact and address details. - Action **List comments** Returns the comments on one Clientary invoice, estimate, project, task, proposal or contract, newest first. - Action **Update contract** Updates an existing Clientary contract: its subject, date, client, status, signers or sections. Only a draft contract can be changed; void and reopen a sent contract first. - Action **Add training images** Uploads training images to a Nanonets OCR model from public image URLs, along with their labelled field annotations, and returns the model's updated state. - Action **Extract data from file** Uploads a document to a Nanonets OCR model and returns the extracted fields and tables for each page. Best for files of three pages or fewer. - Action **Extract data from file asynchronously** Uploads a document to a Nanonets OCR model for background processing and returns the file's request ID; the extracted data is fetched later once processing completes. - Action **Extract data from file URL** Extracts data from a publicly hosted document or image using your Nanonets OCR model and returns the predicted fields and tables. - Action **Extract data from file URL asynchronously** Submits a publicly hosted file to a Nanonets OCR model for asynchronous processing and returns the queued file's ids; fetch the extracted data later with Get prediction file. - Action **Get Model** Returns a Nanonets OCR model's details: its type, training state and the fields (categories) it extracts. - Action **Get prediction file** Returns the prediction results for one processed file, including the model's initial predictions, any review changes, and approval status. - Action **List prediction files** Returns the prediction results for every file uploaded to an OCR model within a date range, split into approved and not-yet-approved pages. ## Each app on its own - [ **Clientary** Online invoicing and time tracking for small businesses and freelancers.](https://apiant.ai/connections/clientary) - [ **Nano Nets** AI platform for extracting data from documents and automating workflows like invoice and claims processing.](https://apiant.ai/connections/nano-nets) Reviews ## What our customers say ## More from Clientary - [ **Clientary to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/clientary-to-hubspot) - [ **Clientary to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/clientary-to-salesforce) - [ **Clientary to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/clientary-to-slack) - [ **Clientary to Google Sheets** Google Sheets](https://apiant.ai/connect/clientary-to-google-sheets) - [ **Clientary to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/clientary-to-gmail) - [ **Clientary to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/clientary-to-google-calendar) ## More into Nano Nets - [ **HubSpot to Nano Nets** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-nano-nets) - [ **Salesforce to Nano Nets** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-nano-nets) - [ **Slack to Nano Nets** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-nano-nets) - [ **Google Sheets to Nano Nets** Google Sheets](https://apiant.ai/connect/google-sheets-to-nano-nets) - [ **Gmail to Nano Nets** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-nano-nets) - [ **Google Calendar to Nano Nets** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-nano-nets) Questions ## Clientary and Nano Nets, answered ### ### What can start an automation from Clientary? Any of Clientary's 3 triggers in the catalog, including New Expense, New Invoice and New Staff. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Nano Nets when something happens in Clientary? Any of Nano Nets's 8 actions, including Add training images, Extract data from file, Extract data from file asynchronously and Extract data from file URL. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Nano Nets to Clientary? Nano Nets has no triggers in the catalog today, so automations start in Clientary. If you need the other direction, ask: your agent reads Nano Nets's API documentation and adds it. ### ### Do I have to build a connector for Clientary or Nano Nets? 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 Clientary and Nano Nets 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.