--- title: "Connect VideoDB to Mindee OCR - APIANT.ai" description: "When \"New Video Uploaded & Indexed\" fires in VideoDB, your agent runs \"Crop document\" in Mindee OCR." canonical: "https://apiant.ai/connect/videodb-to-mindee-ocr" --- # Connect VideoDB to Mindee OCR When **New Video Uploaded & Indexed** fires in [VideoDB](https://apiant.ai/connections/videodb), your agent runs **Crop document** in [Mindee OCR](https://apiant.ai/connections/mindee-ocr). Describe the whole flow and it is built, tested on every scenario and kept running. VideoDB **1** trigger VideoDB **21** actions Mindee OCR **6** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want VideoDB and Mindee 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 VideoDB can start in Mindee OCR - When **New Video Uploaded & Indexed** in VideoDB then **Crop document** in Mindee OCR - When **New Video Uploaded & Indexed** in VideoDB then **Document Data Extraction** in Mindee 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 VideoDB and Mindee OCR ## Triggers and actions 1 trigger · 27 actions - Trigger **New Video Uploaded & Indexed** Triggered when a new video is uploaded to a VideoDB collection. - Action **Add Collection** Creates a new VideoDB collection to organize videos and scope search. - Action **Add Overlay / Watermark** Places an image (logo or watermark) over a VideoDB video at a chosen time and position, and returns a stream URL for the result. - Action **Ask Video (Q&A)** Get the Q&A for a video. - Action **Auto-Chapter Video** Splits a video into scenes (chapters) using shot detection or fixed time segments. The job runs in the background; the result is available at the returned output URL. - Action **Auto-Dub Video** Starts an AI dubbing job that replaces a video's soundtrack with a version in another language, preserving the speaker's voice characteristics. - Action **Check Job Status** Checks the progress of a long-running VideoDB job (dubbing, generation, transcoding, indexing) and returns its status and, once finished, its result. - Action **Create Highlight Clip** Starts an AI clip-generation job on an indexed video from a natural-language prompt describing the moments to include. - Action **Delete Video** Permanently delete a video and all its metadata, transcripts and indexes from VideoDB. - Action **Find Video Moment** Searches one indexed video for the moments matching a spoken-word or visual query, returning each match's start and end time, text and score. - Action **Generate Image** Generates an image from a text prompt using VideoDB's AI generation. Generation runs asynchronously; the result returns a job id and an address to check for the finished image. - Action **Generate Subtitles** Generates subtitles for a video using VideoDB service. - Action **Generate Video** Starts an AI video generation job from a text prompt and saves the result to a collection. - Action **Generate Voice-Over** Converts text into AI-generated speech (a voice-over audio asset) in a VideoDB collection. Generation runs as a job; check its result with Check Job Status or a callback URL. - Action **Get Collection** Retrieve the details of one VideoDB collection by its id. - Action **Get Meeting Assets** Get a meeting recording's status and recorded video URL. - Action **Get Transcript** Get the transcript of a video. - Action **Get Video Metadata** Get metadata for a video. - Action **List Collections** Retrieve all collections in your VideoDB account, including the default collection. - Action **List Videos** Lists the videos in a VideoDB collection. - Action **Summarize Video** Asks VideoDB's AI to summarize a video using your own instructions. Summarization usually runs as a background job: use Check Job Status with the returned job id to fetch the finished summary. - Action **Upload & Index Video** Uploads a video from a URL into a VideoDB collection, waits for the upload to finish, then starts indexing it (spoken words by default) and returns the indexing job. - Action **Crop document** Sends a document to Mindee to be cropped into the individual documents it contains, and returns the queued job. - Action **Document Data Extraction** Sends a document to a Mindee extraction model and returns the queued job, whose results can be fetched once processing finishes. - Action **Find models** Finds models in your Mindee organization by name, optionally limited to one model type. - Action **Get extraction result** Returns the result of a completed document data extraction, including the extracted fields, file details and the options that were used. - Action **Get job** Returns the processing status of a document sent to Mindee, including the link to its result once processing has finished. - Action **Split document** Sends a multi-page document to a Mindee split model, which separates it into individual documents. Returns the queued job; fetch the result once processing finishes. ## Each app on its own - [ **VideoDB** VideoDB is an AI engine for video workflows—search scenes, cut clips, dub, subtitles, and apply GenAI effects.](https://apiant.ai/connections/videodb) - [ **Mindee OCR** Mindee OCR extracts data from the documents you use most.](https://apiant.ai/connections/mindee-ocr) Reviews ## What our customers say ## More from VideoDB - [ **VideoDB to Zoom** Zoom unifies cloud video conferencing, simple online meetings, group messaging, and a software-based...](https://apiant.ai/connect/videodb-to-zoom) - [ **VideoDB to Webflow** Webflow is a professional website builder and CMS for designing, building, and launching responsive...](https://apiant.ai/connect/videodb-to-webflow) - [ **VideoDB 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/videodb-to-wix) - [ **VideoDB to LinkedIn** LinkedIn is a professional networking platform enabling job seekers, companies, and thought leaders to...](https://apiant.ai/connect/videodb-to-linkedin) - [ **VideoDB to Facebook** Facebook is a social media and advertising platform used by individuals and businesses to connect, share...](https://apiant.ai/connect/videodb-to-facebook) - [ **VideoDB to Anthropic** Anthropic builds Claude, a family of large language models.](https://apiant.ai/connect/videodb-to-anthropic) ## More into Mindee OCR - [ **HubSpot to Mindee OCR** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-mindee-ocr) - [ **Salesforce to Mindee OCR** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-mindee-ocr) - [ **Slack to Mindee OCR** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-mindee-ocr) - [ **Google Sheets to Mindee OCR** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-mindee-ocr) - [ **Gmail to Mindee OCR** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-mindee-ocr) - [ **Google Calendar to Mindee OCR** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-mindee-ocr) Questions ## VideoDB and Mindee OCR, answered ### ### What can start an automation from VideoDB? Any of VideoDB's 1 trigger in the catalog, including New Video Uploaded & Indexed. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Mindee OCR when something happens in VideoDB? Any of Mindee OCR's 6 actions, including Crop document, Document Data Extraction, Find models and Get extraction result. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Mindee OCR to VideoDB? Mindee OCR has no triggers in the catalog today, so automations start in VideoDB. If you need the other direction, ask: your agent reads Mindee OCR's API documentation and adds it. ### ### Do I have to build a connector for VideoDB or Mindee 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 VideoDB and Mindee 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.