Cursor can now take an app from a prompt to a live URL. Describe what you want and its cloud agent can build it, provision a Postgres database if needed, and set up sign-in. When you're ready, you pick a URL and hit publish. @cursor_ai runs security checks and handles the hosting. I'd use this for the little internal tools that never make it off my laptop. Build a dashboard for flaky CI tests, put it behind Cursor sign-in, and send your team a link. It's available on all paid plans with cloud agents enabled.

# Cursor Features and Practical Usage 🧩 What if you could call Cursor's AI agent from inside your own scripts and CI checks? The `@cursor/sdk` package grants that wish with a scriptable TypeScript interface to the agent. 🏷️ Title: @cursor/sdk (TypeScript) 🔗 URL: 📘 Overview `@cursor/sdk` exposes the same Cursor agent that powers the IDE, CLI, and web app as a scriptable TypeScript interface. It's built for CI automation, embedded products, and orchestrating custom workflows. It's Node-first, and local agent code loads lazily so cloud-only consumers don't pay the startup cost. ⚙️ How It Works The core concepts are Agent (a stateful container holding conversation context and workspace config), Run (a single prompt submission with its own stream, status, and result), and SDKMessage (normalized stream events emitted during a run). ・`Agent.create()`: validates options and returns a handle immediately; you send prompts via `agent.send()`. ・local / cloud keys: choose where execution happens. `local` runs the agent loop inline in your Node process, while `cloud` runs it in a Cursor-hosted isolated VM with the repo cloned in (a self-hosted VM pool is also supported). ・"Local" only describes where the agent loop runs; model inference goes through Cursor's backend in both modes. ・`local.customTools` lets you expose your own functions as tools (local only). `Agent.prompt()` is a one-shot shortcut. 🛠️ Practical Usage Install with the exact, scoped package name via `npm install @cursor/sdk`. For a CI check against your local working tree, call `Agent.create()` with your `apiKey`, a `model` id, and a `local` cwd, then `agent.send()` a prompt, `await run.wait()`, and check `result.status === "finished"`. To run in the cloud, use the `cloud` key and set `autoCreatePR: true` to open a PR on finish. Authenticate via the `CURSOR_API_KEY` env var or an explicit `apiKey`, using either a user key or a service account key. 💡 Use Cases Run `Agent.prompt()` in PR CI to automate a security audit; use the `cloud` key to spin up many parallel agents that open PRs on separate branches for a large refactor; or wire an internal deployment-check API into the agent via `local.customTools` to embed it in your own workflow. ⚠️ Caveats In local mode, the agent runs shell commands and file edits without approval unless you configure sandboxing or hooks, so consider `local.sandboxOptions: { enabled: true }` in CI. There is no Python SDK; for other languages use the SDK Bridge, or call the Cloud Agents REST API directly. `Agent.resume()` drops inline `mcpServers`, so re-pass them, and model IDs can change, so confirm via `Cursor.models.list()`. #Cursor# #SDK#

Cursor now lets you control agents running on your computer directly from the iOS app You can: • Check what an agent is doing • Reply to it • Start new tasks • Keep directing the work from your phone The agent keeps running on your computer while the phone acts like the remote control So you can literally just walk away from your desk and keep coding from anywhere

# Cursor Features and Practical Usage ☁️ While your machine sleeps, multiple cloud agents work in parallel on separate branches and hand you back review-ready PRs. Cloud Agents free the agent from the "one laptop" constraint. 🏷️ Title: Cloud Agents 🔗 URL: 📘 Overview Cloud Agents are autonomous agents that run in isolated virtual machines rather than locally. You can run many of them at once on dedicated cloud infrastructure and keep work going without keeping your own machine online. Each agent gets a complete development environment in its own VM. ⚙️ How It Works ・Parallel and independent: launch multiple agents simultaneously, each in its own VM, free of local constraints ・Isolated branches: clone the repo from GitHub, GitLab, Azure DevOps Services, or Bitbucket Cloud, work on a separate branch, and push changes as a PR, keeping work isolated until review ・Verifiable: agents receive full context on your codebase and organization so they can run tests and query services to verify their work ・PRs with artifacts: produce merge-ready PRs with screenshots, videos, and logs. You can even remote-control the agent's desktop to test without checking out the branch locally ・Multi-repo: make coordinated changes across separate frontend, backend, infrastructure, or shared-library repositories Agents reach external tools, databases, and APIs via MCP servers, and repository hooks from `.cursor/hooks.json` run too (excluding IDE-specific and user-level hooks). 🛠️ Practical Usage There are many launch paths: Cursor Web ( the Desktop agent dropdown set to `Cloud`, `@cursor` from Slack/GitHub/Linear, the API, the native iOS app, and an Android PWA. The single most important step for effectiveness is configuring `.cursor/environment.json`, which replicates a full dev environment including the cloned repo, dependencies, secrets, startup commands, and network access. You can set it up via agent-led automatic init, saved snapshots, or a Dockerfile. 💡 Use Cases In the morning, fan out several tasks to the cloud ("investigate this bug and open a fix PR"), and by midday you have a queue of review-ready PRs. Because agents run tests and query APIs autonomously, humans can focus on review. ⚠️ Caveats Agents need read-write access to your repo and dependent repos/submodules, and a paid plan is required. Manage secrets via the Secrets tab in the dashboard rather than `.env.local`. User-level `~/.cursor/hooks.json` is unavailable to cloud VMs. Pricing is standard API billing for the selected model, and you set a spend limit before first use. You can select the context window size for supported models, and a larger window increases token usage and cost. Supported source control providers are GitHub, GitLab, Azure DevOps Services, and Bitbucket Cloud. #Cursor# #CloudAgents#

Cursor went through 4 or 5 ideas before finding PMF, all within a year. Launch fast. Kill what doesn’t work. Keep narrowing until something does. What’s stopping you from launching?

# Cursor Features and Practical Usage 🌐 "Just look at the screen and fix it" is now something the AI agent can literally do. Cursor's Browser tool hands the agent control of a browser, covering everything from E2E testing to design-to-code in one loop. 🏷️ Title: Browser Tool 🔗 URL: 📘 Overview The Browser tool lets Cursor's agent directly drive a browser inside the IDE. It can navigate to URLs, click, fill forms, capture screenshots, and inspect console logs and network traffic on its own. The key benefit is closing the loop between visual verification and code changes within a single agent run. ⚙️ How It Works The browser runs as a secure web view controlled via an MCP server extension, and the agent can: ・Navigate: visit URLs, follow links, move through history, reload pages ・Interact: click, double-click, right-click, hover, fill and submit forms ・Inspect visually: capture screenshots as images to verify layout and UI ・Debug: read JavaScript console logs and errors, plus network traffic Logs are written to files and the agent selectively reads only the relevant lines, so it handles huge outputs efficiently. Automatic dev-server detection prevents starting duplicate servers. Authentication cookies, localStorage, sessionStorage, and IndexedDB persist across sessions in the same workspace, so login state survives between verification runs. 🛠️ Practical Usage The design sidebar lets you design and code at the same time. You can visually adjust element positioning, flex direction, alignment, grid layouts, width/height/padding/margin, colors, gradients, shadows, opacity, and border radius with sliders. When the look matches your vision, click `Apply` and an agent translates the visual changes into appropriate code. You can also select multiple elements and apply changes together via hot-reload. Execution safety is governed by approval modes: `Manual approval` (recommended), `Allow-listed actions`, and `Auto-run`. 💡 Use Cases ・E2E testing: fill forms with test data, validate error messages, capture screenshots for visual regression ・Design-to-code: import Figma mockups and convert to pixel-perfect HTML/CSS ・Accessibility audits: check contrast ratios, semantic HTML, ARIA labels, and keyboard navigation against WCAG ⚠️ Caveats The origin allowlist provides best-effort protection only. Link navigation and client-side redirects from allowed domains may still reach non-allowed origins, and manual user navigation bypasses the allowlist entirely. Avoid `Auto-run` with untrusted code, and review allowlist configurations regularly. #Cursor# #AICoding#