--- title: "Connect Cursor to Google Vertex AI - APIANT.ai" description: "When \"Agent Pull Request Created\" fires in Cursor, your agent runs \"Analyze Document\" in Google Vertex AI." canonical: "https://apiant.ai/connect/cursor-to-google-vertex-ai" --- # Connect Cursor to Google Vertex AI When **Agent Pull Request Created** fires in [Cursor](https://apiant.ai/connections/cursor), your agent runs **Analyze Document** in [Google Vertex AI](https://apiant.ai/connections/google-vertex-ai). Describe the whole flow and it is built, tested on every scenario and kept running. Cursor **3** triggers Cursor **11** actions Google Vertex AI **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 Cursor and Google Vertex AI 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 Cursor can start in Google Vertex AI - When **Agent Pull Request Created** in Cursor then **Analyze Document** in Google Vertex AI - When **New Agent** in Cursor then **Send Prompt** in Google Vertex AI 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 Cursor and Google Vertex AI ## Triggers and actions 3 triggers · 23 actions - Trigger **Agent Pull Request Created** Triggers when the selected Cursor cloud agent opens a new GitHub pull request. - Trigger **Agent Status Equals** Triggers when a run on the chosen Cursor agent reaches the status you select, such as Finished or Error. - Trigger **New Agent** Triggered when a new Cursor cloud agent is created. - Action **Add Followup Instruction to Agent** Sends a follow-up instruction to an existing Cursor cloud agent, either starting a new run or steering the run in progress. Returns the new run or how the steer was delivered. - Action **Cancel run** Cancels the active run of a Cursor cloud agent. The run ends in the Cancelled state; start a new run to continue the conversation. - Action **Delete Agent** Permanently deletes a Cursor cloud agent. This cannot be undone. Returns the ID of the deleted agent. - Action **Find Agent Status** Looks up a Cursor cloud agent by its ID and returns its status, name, repositories, latest run and link. - Action **Get run** Returns the status, timestamps, duration, final reply and pushed branches for one run of a Cursor cloud agent. - Action **Launch Agent** Creates a Cursor cloud agent and immediately starts its first run on the task you describe. Returns the new agent and its run. - Action **List agents** Returns the Cursor cloud agents for the connected user, newest first, optionally filtered by pull request URL. - Action **List artifacts** Returns the files a Cursor cloud agent has produced, with each file's path, size and last modified time. Returns at most 100 artifacts. - Action **List models** Returns the recommended Cursor models you can choose from when creating an agent, including their names, aliases, parameters and variants. - Action **List repositories** Returns the GitHub repositories the connected Cursor user can access through Cursor's GitHub App installation. - Action **List runs** Returns the runs of a Cursor cloud agent, newest first, including each run's status, duration, and final reply. - Action **Analyze Document** Analyzes a document (PDF, image, or text file) using Gemini Vision to extract insights, summaries, or structured data. - Action **Analyze Text Sentiment** Analyzes text for positive or negative sentiment. - Action **Classify Text** Classify some text from amongst a list of categories. - Action **Conversation** Sends a chat message, optionally storing messages as you go. - Action **Count Tokens** Returns how many tokens a prompt uses for a Gemini model on Vertex AI. - Action **Generate Code** Generates, explains, refactors, debugs, or converts code using AI. Supports multiple programming languages. - Action **Generate Embeddings** Generates vector embeddings for text. Useful for semantic search, RAG, and similarity comparisons. - Action **Generate Image** Generates an image from a prompt. - Action **Send Prompt** Sends a prompt and generates a completion. - Action **Summarize Text** Summarizes text. - Action **Translate Text** Translates text between languages using AI with support for different tones and styles. - Action **Write an Email** Writes the content of an email based on your provided prompt for use in a subsequent step. ## Each app on its own - [ **Cursor** Cursor is an AI-powered code editor that understands your codebase, supports natural-language coding...](https://apiant.ai/connections/cursor) - [ **Google Vertex AI** Build, deploy, and scale machine learning (ML) models, with fully managed ML tools for any use case, with...](https://apiant.ai/connections/google-vertex-ai) Reviews ## What our customers say ## More from Cursor - [ **Cursor to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/cursor-to-hubspot) - [ **Cursor to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/cursor-to-salesforce) - [ **Cursor to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/cursor-to-slack) - [ **Cursor to Google Sheets** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/cursor-to-google-sheets) - [ **Cursor to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/cursor-to-gmail) - [ **Cursor to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/cursor-to-google-calendar) ## More into Google Vertex AI - [ **HubSpot to Google Vertex AI** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-google-vertex-ai) - [ **Salesforce to Google Vertex AI** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-google-vertex-ai) - [ **Slack to Google Vertex AI** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-google-vertex-ai) - [ **Google Sheets to Google Vertex AI** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-google-vertex-ai) - [ **Gmail to Google Vertex AI** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-google-vertex-ai) - [ **Google Calendar to Google Vertex AI** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-google-vertex-ai) Questions ## Cursor and Google Vertex AI, answered ### ### What can start an automation from Cursor? Any of Cursor's 3 triggers in the catalog, including Agent Pull Request Created, New Agent and Agent Status Equals. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Google Vertex AI when something happens in Cursor? Any of Google Vertex AI's 12 actions, including Send Prompt, Analyze Document, Analyze Text Sentiment and Classify Text. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Google Vertex AI to Cursor? Google Vertex AI has no triggers in the catalog today, so automations start in Cursor. If you need the other direction, ask: your agent reads Google Vertex AI's API documentation and adds it. ### ### Do I have to build a connector for Cursor or Google Vertex AI? 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 Cursor and Google Vertex AI 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.