# Connect Crowdin to Browserbase When **Comment/Issue Added** fires in [Crowdin](https://apiant.ai/connections/crowdin), your agent runs **Fetch page** in [Browserbase](https://apiant.ai/connections/browserbase). Describe the whole flow and it is built, tested on every scenario and kept running. Crowdin **12** triggers Crowdin **29** actions Browserbase **12** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Crowdin and Browserbase to do together? Give your AI client this address. `https://mcp.apiant.ai` 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 Crowdin can start in Browserbase - When **Comment/Issue Added** in Crowdin then **Fetch page** in Browserbase - When **Comment/Issue Updated** in Crowdin then **Add context** in Browserbase 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 Crowdin and Browserbase ## Triggers and actions 12 triggers · 41 actions - Trigger **Comment/Issue Added** Triggers when a user creates a comment or an issue. - Trigger **Comment/Issue Deleted** Triggers when a user deletes a comment or an issue. - Trigger **Comment/Issue Updated** Triggers when a user updates a comment or an issue. - Trigger **File Added** Triggers when a new file has been added to the project. - Trigger **File Approved** Triggers when a file is fully translated and approved. - Trigger **File Deleted** Triggers when a file has been deleted from the project. - Trigger **File Reverted** Triggers when a file update has been reverted. - Trigger **File Translated** Triggers when a file is fully translated. - Trigger **File Updated** Triggers when a file has been updated. - Trigger **New Directory** Triggers when a new directory is created in a Crowdin project. - Trigger **New Label** Triggers when a new label is added to a Crowdin project. - Trigger **New Project** Triggers when a new project is created in Crowdin. - Action **Add Approval** Approves a translation (or a source-string correction) in a Crowdin project. - Action **Add Translation** Adds a translation in a target language to a source string in a Crowdin project, or uploads a translated asset file. - Action **Create Comment** Adds a comment or issue to a string or asset file in a Crowdin project. - Action **Create Directory** Creates a directory in a Crowdin project, optionally inside a branch or parent directory. - Action **Create Label** Creates a new label in a Crowdin project, which can then be assigned to strings or screenshots. - Action **Create or Update a File** Uploads a source file to a Crowdin project, adding it as a new file or, when an existing file ID is given, replacing that file's content. - Action **Create Project** Creates a new translation project in Crowdin with the chosen source and target languages and project settings. - Action **Create String** Creates a source string for translation in a file of a Crowdin project. - Action **Create Task** Creates a translation or proofreading task in a Crowdin project for chosen files, directories, branches or strings. - Action **Delete Comment** Deletes a string or asset comment or issue from a Crowdin project. - Action **Delete File** Deletes a source file from a Crowdin project. - Action **Download Translated File** Builds the translated version of a project file for one target language and returns a temporary download link for it. - Action **Find Directory** Finds directories in a Crowdin project by name. - Action **Find File** Finds source files in a Crowdin project whose name matches the text you give, optionally limited to a branch or directory. - Action **Find Label** Finds labels in a Crowdin project whose title matches the title you supply. - Action **Find Language** Finds a Crowdin language by its name or language code (for example "Spanish" or "es") and returns its codes and details. - Action **Find Project** Finds Crowdin projects whose name matches the text you supply, returning the first match and the full list. - Action **Find String** Finds source strings in a Crowdin project by text, identifier or context, returning the first match and the full list. - Action **Find Task** Finds a task in a Crowdin project by its title, optionally narrowed by status or batch, and returns the first match. - Action **Get Comment** Returns a single string or asset comment (or issue) in a Crowdin project, including its text, author, issue status and attachments. - Action **Get Screenshot** Returns a screenshot from a Crowdin project, including its name, image link, size, tags and labels. - Action **Get Translation** Returns a single translation of a string or asset in a Crowdin project, including its text, author, rating and provider. - Action **Label String** Assigns a label to one or more strings in a Crowdin project and returns the updated strings. - Action **List Approvals** Returns the approvals on translations in a Crowdin project, filtered by translation, correction or language. - Action **Remove Label From String** Removes a label from one or more strings in a Crowdin project and returns the updated strings. - Action **Resolve Issue** Marks an issue reported on a Crowdin string or asset as resolved and returns the updated issue. - Action **Restore File Revision** Restores a Crowdin source file to one of its previous revisions and returns the restored file. - Action **Translation Progress** Returns the translation and approval progress of a Crowdin project for each of its target languages. - Action **Upload Screenshot** Uploads an image and adds it as a screenshot to a Crowdin project, optionally auto-tagging strings and attaching labels. - Action **Add context** Creates a new browser Context that persists cookies and storage across Browserbase sessions. - Action **Add session** Creates a new Browserbase browser session and returns its id along with the URLs used to connect to it. - Action **Delete context** Deletes a browser context (saved cookies and browser state) from your Browserbase project. - Action **Fetch page** Fetches a web page through Browserbase and returns its content (raw, markdown, or schema-extracted JSON), status code and headers. - Action **Get context** Returns a Browserbase context (saved browser state) by its id, including its name, project and timestamps. - Action **Get run** Returns the current status and details of an agent run, including its result and the browser session it used. - Action **Get session** Returns a Browserbase browser session, including its status, region, timestamps and connection URLs. - Action **List downloads** Returns the files downloaded during a Browserbase session, optionally filtered by filename, MIME type, size or creation time. - Action **List sessions** Returns the browser sessions in your Browserbase project, optionally filtered by status or by user metadata. - Action **Run agent** Starts a Browserbase browser agent run that completes a natural-language task using web search and browser tools. Returns the new run, which starts in a pending state. - Action **Search web** Runs a web search through Browserbase and returns the matching pages with their titles and URLs. - Action **Update session** Updates a Browserbase session, such as requesting that it be released before its timeout to stop further charges. ## Each app on its own - [ **Crowdin** Crowdin is a cloud-based solution that streamlines localization management for your team.](https://apiant.ai/connections/crowdin) - [ **Browserbase** Cloud browser infrastructure API for running headless browsers to power AI agent web automation and scraping.](https://apiant.ai/connections/browserbase) Reviews ## What our customers say ## More from Crowdin - [ **Crowdin to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/crowdin-to-hubspot) - [ **Crowdin to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/crowdin-to-salesforce) - [ **Crowdin to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/crowdin-to-slack) - [ **Crowdin to Google Sheets** Google Sheets](https://apiant.ai/connect/crowdin-to-google-sheets) - [ **Crowdin to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/crowdin-to-gmail) - [ **Crowdin to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/crowdin-to-google-calendar) ## More into Browserbase - [ **HubSpot to Browserbase** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-browserbase) - [ **Salesforce to Browserbase** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-browserbase) - [ **Slack to Browserbase** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-browserbase) - [ **Google Sheets to Browserbase** Google Sheets](https://apiant.ai/connect/google-sheets-to-browserbase) - [ **Gmail to Browserbase** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-browserbase) - [ **Google Calendar to Browserbase** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-browserbase) Questions ## Crowdin and Browserbase, answered ### ### What can start an automation from Crowdin? Any of Crowdin's 12 triggers in the catalog, including Comment/Issue Added, Comment/Issue Updated, File Added and File Updated. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Browserbase when something happens in Crowdin? Any of Browserbase's 12 actions, including Update session, Add context, Add session and Fetch page. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Browserbase to Crowdin? Browserbase has no triggers in the catalog today, so automations start in Crowdin. If you need the other direction, ask: your agent reads Browserbase's API documentation and adds it. ### ### Do I have to build a connector for Crowdin or Browserbase? 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. ### ### 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.