--- title: "Connect GitHub to Veryfi OCR - APIANT.ai" description: "When \"New Branch\" fires in GitHub, your agent runs \"Classify Document\" in Veryfi OCR." canonical: "https://apiant.ai/connect/github-to-veryfi-ocr" --- # Connect GitHub to Veryfi OCR When **New Branch** fires in [GitHub](https://apiant.ai/connections/github), your agent runs **Classify Document** in [Veryfi OCR](https://apiant.ai/connections/veryfi-ocr). Describe the whole flow and it is built, tested on every scenario and kept running. GitHub **15** triggers GitHub **19** actions Veryfi OCR **15** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want GitHub and Veryfi OCR 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 GitHub can start in Veryfi OCR - When **New Branch** in GitHub then **Classify Document** in Veryfi OCR - When **New Collaborator** in GitHub then **Convert Document To Markdown** in Veryfi OCR 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 GitHub and Veryfi OCR ## Triggers and actions 15 triggers · 34 actions - Trigger **Issue Closed** Triggers when an issue in a repository is closed. - Trigger **New Branch** Triggers when a new branch is created in a GitHub repository. - Trigger **New Collaborator** Triggers when a new collaborator is added to a GitHub repository. - Trigger **New Commit** Triggers when a new commit is pushed to a GitHub repository's default branch. - Trigger **New Commit Comment** Triggers when someone comments on a commit in a repository. - Trigger **New Gist** Triggers when you create a new gist on GitHub. - Trigger **New Global Event** Triggers when a new public event happens anywhere on GitHub, such as a push, fork, or new issue. - Trigger **New Issue** Triggers when a new issue is created in a repository. - Trigger **New Label** Triggers when a new label is added to a GitHub repository. - Trigger **New Milestone** Triggers when a new milestone is created in a repository. - Trigger **New Pull Request** Triggers when a new pull request is opened in a repository. - Trigger **New Release** Triggers when a new release is published in a GitHub repository. - Trigger **New Repo Event** Triggers when new activity (pushes, issues, pull requests, releases and more) happens in a GitHub repository. - Trigger **New Repository** Triggers when a new public repository appears under a GitHub user or organization. - Trigger **New Watcher** Triggers when someone starts watching a repository. - Action **Add Labels to Issue** Adds labels to an issue or pull request in a GitHub repository, keeping its existing labels. - Action **Check Organization Membership** Checks whether a GitHub user is a member of an organization and returns true or false. - Action **Create Branch** Creates a new branch in a repository, starting from the commit you choose. - Action **Create Comment** Adds a comment to an issue or pull request in a GitHub repository. - Action **Create Gist** Creates a new gist with one file on the connected GitHub account. - Action **Create Issue** Creates a new issue in a GitHub repository. - Action **Create or Update File** Creates a new file in a repository, or replaces an existing file's contents, as a commit. - Action **Create Pull Request** Opens a pull request asking to merge one branch into another. - Action **Delete Branch** Deletes a branch from a repository. Any open pull request from that branch is closed. - Action **Find Branch** Finds a branch in a GitHub repository by name and returns its latest commit and protection status. - Action **Find Issue** Finds an issue in a GitHub repository by its number and returns its title, body, state, author and labels. - Action **Find Organization** Finds a GitHub organization by its login and returns its profile details. - Action **Find Pull Request** Finds a pull request in a GitHub repository by its number and returns its title, state, branches and merge status. - Action **Find Repository** Returns a GitHub repository by its owner and name, including its description, visibility, default branch and counts. - Action **Find User** Finds a GitHub user by username and returns their public profile. - Action **Get File Contents** Returns a file from a GitHub repository, with its base64-encoded content, at the default branch or a chosen branch, tag or commit. - Action **Submit Review** Submits a review on a pull request: approve it, request changes, or leave a review comment. - Action **Update Issue** Updates an existing issue in a GitHub repository, such as its title, text, state, labels or assignees. - Action **Update Pull Request** Changes a pull request's title, description, target branch, or open/closed state. - Action **Classify Document** Classifies a document (receipt, invoice, W-9, check, bank statement, etc.) and returns the predicted document type with a confidence score. - Action **Convert Document To Markdown** Upload a document (image/PDF) and convert its content to markdown text. - Action **Extract Data From Any Document** Extracts data from the supplied document - Action **Extract Data From Bank Check** Extracts data from the supplied bank check - Action **Extract Data From Bank Statement** Submits a bank statement (by URL, base64 data or S3 path) to Veryfi and returns the extracted statement data, including account details, balances and transactions. - Action **Extract Data From Business Card** Upload a business card image/PDF and extract structured contact data (name, company, phone, email, address). - Action **Extract Data From Contract** Submits a contract (PDF or ZIP, up to 20 MB) to Veryfi and returns the extracted contract data such as parties, dates, term, total and governing law. - Action **Extract Data From Driver License** Extracts the holder's details from a US driver license image or PDF using Veryfi's us_driver_license blueprint. - Action **Extract Data From Invoice** Extracts data from the supplied invoice - Action **Extract Data From Passport** Extracts data from the supplied passport - Action **Extract Data From W2 Form** Submits a W-2 form (image or PDF) to Veryfi and returns the extracted wage, tax, employer and employee data. - Action **Extract Data From W-8BEN-E Form** Submits a W-8BEN-E form (image or PDF) to Veryfi and returns the data extracted from it. - Action **Extract Data From W9 Form** Extracts data from the supplied W9 form - Action **Extracts Data From Receipt** Submits a receipt image or PDF to Veryfi and returns the extracted receipt data, including the merchant, date, totals, tax and line items. - Action **Get Contract** Fetches a processed contract by ID, including its extracted text and data, source file details and PDF link. An error occurs if the contract is not found. ## Each app on its own - [ **GitHub** GitHub is the perfect place to share code and work collaboratively on private and open source software.](https://apiant.ai/connections/github) - [ **Veryfi OCR** Veryfi OCR is a multi-model platform that extracts structured data from any document, such as receipts...](https://apiant.ai/connections/veryfi-ocr) Reviews ## What our customers say ## More from GitHub - [ **GitHub to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/github-to-hubspot) - [ **GitHub to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/github-to-salesforce) - [ **GitHub to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/github-to-slack) - [ **GitHub to Google Sheets** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/github-to-google-sheets) - [ **GitHub to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/github-to-gmail) - [ **GitHub to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/github-to-google-calendar) ## More into Veryfi OCR - [ **Trello to Veryfi OCR** Trello is a visual collaboration tool that organizes projects into boards, lists, and cards.](https://apiant.ai/connect/trello-to-veryfi-ocr) - [ **HubSpot to Veryfi OCR** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-veryfi-ocr) - [ **Salesforce to Veryfi OCR** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-veryfi-ocr) - [ **Slack to Veryfi OCR** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-veryfi-ocr) - [ **Google Sheets to Veryfi OCR** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-veryfi-ocr) - [ **Gmail to Veryfi OCR** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-veryfi-ocr) Questions ## GitHub and Veryfi OCR, answered ### ### What can start an automation from GitHub? Any of GitHub's 15 triggers in the catalog, including New Branch, New Collaborator, New Commit and New Commit Comment. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Veryfi OCR when something happens in GitHub? Any of Veryfi OCR's 15 actions, including Classify Document, Convert Document To Markdown, Extract Data From Any Document and Extract Data From Bank Check. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Veryfi OCR to GitHub? Veryfi OCR has no triggers in the catalog today, so automations start in GitHub. If you need the other direction, ask: your agent reads Veryfi OCR's API documentation and adds it. ### ### Do I have to build a connector for GitHub or Veryfi OCR? 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 GitHub and Veryfi OCR 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.