# Mobilebox

> Mobile sandboxes for AI agents. Mobilebox runs cloud Android 14 phones (arm64), iPhone and iPad, and real Android devices that your agent controls over a REST API or a hosted MCP server with 14 tools. The agent reads the screen as numbered elements, acts with taps, typing and swipes, installs APKs, and parks the phone to keep apps, data and logins. Your agent supplies the reasoning; Mobilebox supplies the phone.

## Pricing
- Cloud Android phone: $0.01 per ready phone-minute, billed per second, one-minute minimum per session. Boot time and parked phones are free.
- iPhone and iPad: $0.05 per phone-minute. Real Android device: $0.03 per phone-minute. Dedicated devices from $79 a month; volume over 100 devices through sales.
- Your agent sets you up: [setup.md](https://mobilebox.dev/setup.md?via=llms) (your email, and the agent gets its own key at once; the 6-digit code from your inbox keeps the workspace). Or sign up at https://mobilebox.dev/signup?via=llms. New workspaces get free credit. Add credits from the dashboard.
- Requests: up to 20 actions per call, 256 KB of JSON, waits up to 55 s. Phones park after 5 idle minutes, and after 15 minutes of running unless max_duration asks for up to 3 hours.
- iPhone and iPad: create with platform: "ios". Real Android: device: "real". Pages: [iPhone and iPad](https://mobilebox.dev/ios?via=llms), [real Android devices](https://mobilebox.dev/real-devices?via=llms). Details: https://mobilebox.dev/docs/reference?via=llms#devices.

## Connect
- MCP: https://mobilebox.dev/mcp (stateless Streamable HTTP; header Authorization: Bearer API_KEY). Tools: list_phones, create_phone, start_phone, park_phone, delete_phone, set_device, install_app, list_apps, uninstall_app, observe, act, screenshot, watch_phone, request_capability.
- One-click: add https://mobilebox.dev/mcp as a connector in Claude, ChatGPT, Cursor or Claude Code with no key; the client signs your user in over MCP OAuth ([how](https://mobilebox.dev/docs/reference?via=llms#mcp-sign-in)).
- Setup per coding tool: [Claude Code](https://mobilebox.dev/blog/android-agent-mcp?via=llms), [Cursor, Codex and VS Code](https://mobilebox.dev/blog/android-mcp-cursor-codex-vscode?via=llms), [Gemini CLI](https://mobilebox.dev/blog/gemini-cli-android-mcp?via=llms), [Windsurf](https://mobilebox.dev/blog/windsurf-android-mcp?via=llms), [Cline](https://mobilebox.dev/blog/cline-android-mcp?via=llms), [GitHub Copilot](https://mobilebox.dev/blog/github-copilot-android-mcp?via=llms).
- REST: https://mobilebox.dev/v1 with the same key; schemas in [OpenAPI](https://mobilebox.dev/openapi.json?via=llms).
- Python: `pip install mobilebox` is the REST client ([PyPI](https://pypi.org/project/mobilebox/)), `pip install langchain-mobilebox` its LangChain and LangGraph tools ([PyPI](https://pypi.org/project/langchain-mobilebox/)); both read MOBILESANDBOX_API_KEY. How-to: [an Android phone for your Python AI agent](https://mobilebox.dev/blog/android-phone-for-python-ai-agent?via=llms).
- Agent keys: the agent gets its own through [setup.md](https://mobilebox.dev/setup.md?via=llms) (POST /v1/signup/email returns it at once; /v1/signup/verify with the emailed code confirms it), or your user creates one in the dashboard. Public discovery does not authenticate the client. Never put keys in prompts.

## Pages
- [Mobile sandbox for AI agents](https://mobilebox.dev/mobile-sandbox?via=llms): what a mobile sandbox is and how an agent uses one.
- [AI sandboxes for agents](https://mobilebox.dev/ai-sandbox?via=llms): code, browser or phone sandbox, and which one a task needs.
- [Phone agents](https://mobilebox.dev/phone-agent?via=llms): give an AI agent a phone it can use (not a voice-call agent).
- [App automation with AI agents](https://mobilebox.dev/app-automation?via=llms): test your own app, or run tasks in apps with your own account.
- [Android MCP server](https://mobilebox.dev/android-mcp-server?via=llms): the hosted Android MCP server, how to connect any client, every tool, hosted or local.
- [Live view](https://mobilebox.dev/live-view?via=llms): watch your AI agent use a phone live, every tap, swipe and keystroke drawn and captioned. Open it with watch_phone, POST /v1/phones/{id}/view or npx mobilebox watch <phone_id>.
- [iPhone and iPad](https://mobilebox.dev/ios?via=llms) and [real Android devices](https://mobilebox.dev/real-devices?via=llms): the same API and MCP on every device.
- [Changelog](https://mobilebox.dev/changelog?via=llms): what shipped, newest first, dated.
- [About](https://mobilebox.dev/about?via=llms): who builds Mobilebox, contact and support.
- [Benchmarks](https://mobilebox.dev/benchmarks?via=llms): measured cold start, tap latency, APK install and 10-minute cost for cloud Android services and a CI emulator (Nov 2026), with CSV and scripts.

## Integrations
Each page has a runnable example (the code creates a phone over REST, the agent drives it, the phone is deleted in finally). All: [Integrations](https://mobilebox.dev/integrations?via=llms).
- [OpenAI Agents SDK](https://mobilebox.dev/integrations/openai-agents?via=llms): Python, mCP through MCPServerStreamableHttp. Example: https://github.com/fifteenA/mobilebox/blob/main/examples/integrations/openai-agents/agent.py
- [LangGraph](https://mobilebox.dev/integrations/langgraph?via=llms): Python, the langchain-mobilebox tools over REST. Example: https://github.com/fifteenA/mobilebox/tree/main/packages/python/langchain-mobilebox
- [CrewAI](https://mobilebox.dev/integrations/crewai?via=llms): Python, mCP through MCPServerHTTP. Example: https://github.com/fifteenA/mobilebox/blob/main/examples/integrations/crewai/agent.py
- [browser-use](https://mobilebox.dev/integrations/browser-use?via=llms): Python, two custom actions over REST. Example: https://github.com/fifteenA/mobilebox/blob/main/examples/integrations/browser-use/agent.py
- [Mastra](https://mobilebox.dev/integrations/mastra?via=llms): TypeScript, mCP through MCPClient. Example: https://github.com/fifteenA/mobilebox/blob/main/examples/integrations/mastra/agent.ts
- [Vercel AI SDK](https://mobilebox.dev/integrations/vercel-ai-sdk?via=llms): TypeScript, mCP through createMCPClient. Example: https://github.com/fifteenA/mobilebox/blob/main/examples/integrations/vercel-ai-sdk/agent.ts
- [Claude Agent SDK](https://mobilebox.dev/integrations/claude-agent-sdk?via=llms): TypeScript, mCP through mcpServers. Example: https://github.com/fifteenA/mobilebox/blob/main/examples/integrations/claude-agent-sdk/agent.ts

## Questions answered
- [How can Claude Code test my Android app?](https://mobilebox.dev/blog/claude-code-android-app-testing?via=llms)
- [How do I run an Android emulator in CI without KVM?](https://mobilebox.dev/blog/android-emulator-without-kvm?via=llms)
- [How do I run an APK in the cloud via an API?](https://mobilebox.dev/blog/android-emulator-without-kvm?via=llms)
- [Which cloud Android phones can AI agents use (Mobilerun or Limrun alternatives)?](https://mobilebox.dev/blog/cloud-android-for-ai-agents-compared?via=llms)
- [Which Android MCP server should I use, hosted or local (mobile-mcp)?](https://mobilebox.dev/blog/android-mcp-server-hosted-vs-local?via=llms)
- [How do I give my coding agent an Android phone over MCP?](https://mobilebox.dev/blog/android-agent-mcp?via=llms)
- [How do I smoke-test an APK in GitHub Actions without a local emulator?](https://mobilebox.dev/blog/android-apk-ci-smoke-tests?via=llms)
- [How can an AI coding agent test an iOS app?](https://mobilebox.dev/blog/ios-testing-for-ai-coding-agents?via=llms)
- [Does my agent need a real Android device or a cloud phone?](https://mobilebox.dev/blog/real-android-devices-vs-cloud-phones?via=llms)
- [How do I test an iPhone app my agent built?](https://mobilebox.dev/blog/test-iphone-apps-your-agent-built?via=llms)
- [Mobilebox or Firebase Test Lab for Android testing?](https://mobilebox.dev/blog/mobilebox-vs-firebase-test-lab?via=llms)
- [Cloud phone or a local Android emulator for my agent?](https://mobilebox.dev/blog/mobilebox-vs-local-emulator?via=llms)
- [Mobilebox, Limrun or Mobilerun: which fits my agent?](https://mobilebox.dev/blog/mobilebox-vs-limrun?via=llms)
- [How do I give Cursor, Codex or VS Code an Android phone?](https://mobilebox.dev/blog/android-mcp-cursor-codex-vscode?via=llms)
- [Can my agent run 50 phones in parallel?](https://mobilebox.dev/blog/run-android-phones-in-parallel?via=llms)
- [Can each phone get its own residential IP?](https://mobilebox.dev/blog/residential-ip-per-phone?via=llms)
- [What does Mobilebox cost for a team?](https://mobilebox.dev/blog/mobilebox-pricing-for-teams?via=llms)
- [How fast do cloud Android phones for AI agents start?](https://mobilebox.dev/blog/cloud-android-start-time-benchmark?via=llms)
- [What is a cloud phone for AI agents?](https://mobilebox.dev/blog/what-is-a-cloud-phone-for-ai-agents?via=llms)
- [Which are the best Android MCP servers?](https://mobilebox.dev/blog/best-android-mcp-servers?via=llms)
- [Which are the best cloud phones for AI agents?](https://mobilebox.dev/blog/best-cloud-phones-for-ai-agents?via=llms)
- [How do I give my Python AI agent an Android phone?](https://mobilebox.dev/blog/android-phone-for-python-ai-agent?via=llms)
- [What is the cheapest cloud Android phone for AI agents per minute?](https://mobilebox.dev/blog/cheapest-cloud-android-phone-per-minute?via=llms)
- [Is there an E2B-style sandbox for Android apps?](https://mobilebox.dev/blog/android-vs-agent-sandboxes?via=llms)

## Start
- [Setup](https://mobilebox.dev/setup.md?via=llms): for agents. Sign up with your user's email code, store the key, add MCP, open a first phone.
- [Quickstart](https://mobilebox.dev/docs/index.md?via=llms): Runnable Node and Python lifecycle and authentication.
- [Agent guide](https://mobilebox.dev/skill.md?via=llms): Observe, act, verify, park.
- [API reference](https://mobilebox.dev/docs/reference.md?via=llms): REST endpoints, request sizes and response semantics.
- [Errors](https://mobilebox.dev/docs/errors.md?via=llms): Recovery and partial failures.
- [OpenAPI](https://mobilebox.dev/openapi.json?via=llms): REST schemas including the shared action vocabulary.
- [GitHub](https://github.com/fifteenA/mobilebox): the public repo, with MCP server and REST API examples.

## Reading
- [Give your coding agent an Android sandbox over MCP](https://mobilebox.dev/blog/android-agent-mcp?via=llms): Add the remote MCP server to Claude Code or Cursor, see every phone tool, run a bounded first task and know what is proven.
- [Does this task need a phone or a browser?](https://mobilebox.dev/blog/native-app-or-browser?via=llms): Choose the smallest runtime that can actually complete the task: HTTP, browser, or native Android.
- [Mobilebox or Mobilerun: where do the agent and the phone run?](https://mobilebox.dev/blog/mobilebox-vs-mobilerun?via=llms): Compare Mobilebox’s hosted Android API and MCP with Mobilerun’s framework, coding-agent harness, hosted agent and cloud phones.
- [Mobilebox or Appium for Android automation?](https://mobilebox.dev/blog/mobilebox-vs-appium?via=llms): Separate a managed phone runtime from a test automation framework before choosing your Android stack.
- [Android, E2B, Browserbase: which sandbox fits?](https://mobilebox.dev/blog/android-vs-agent-sandboxes?via=llms): Is there an E2B-style sandbox for Android apps? Yes: compare Linux, browser and Android sandboxes by the surface your agent controls and the state each keeps.
- [Why your agent tapped the wrong thing](https://mobilebox.dev/blog/screen-refs-and-recovery?via=llms): Understand stale screen references, choose stable targets, and recover without repeating side effects.
- [Batch the steps you know. Observe the ones you don’t.](https://mobilebox.dev/blog/batch-android-actions?via=llms): Build bounded Android action batches, inspect partial failure, and verify the resulting screen.
- [Install APKs and split bundles over an API](https://mobilebox.dev/blog/install-apk-split-bundles?via=llms): Upload APK bytes or install by URL, handle arm64 split bundles, and diagnose update failures.
- [Keep the login. Stop the running phone.](https://mobilebox.dev/blog/park-resume-android?via=llms): Understand what park and resume preserve, what restarts, and when to delete an Android sandbox.
- [Put a budget around your Android agent](https://mobilebox.dev/blog/android-sandbox-costs?via=llms): Use idle timeouts, session caps, account balance, and session records to control phone runtime costs.
- [Timezone, locale, GPS and IP are four different inputs](https://mobilebox.dev/blog/locale-location-proxy?via=llms): Configure an Android sandbox for regional workflows without confusing locale or GPS with network egress.
- [A successful tap is not a successful task](https://mobilebox.dev/blog/verify-agent-workflows?via=llms): Design Android agent checks around outcomes, screen evidence, failure traces, and safe cleanup.
- [Screenshot or accessibility tree? Choose the evidence your agent needs](https://mobilebox.dev/blog/screenshot-vs-accessibility-tree?via=llms): Choose structured Android observations for labels and state, screenshots for pixels, and synchronized evidence when both matter.
- [Run an APK smoke test from CI without a local emulator](https://mobilebox.dev/blog/android-apk-ci-smoke-tests?via=llms): A complete Node script and GitHub Actions job that installs an APK on a remote Android sandbox, checks its first screen and deletes the phone even when the check fails.
- [Mobilebox or BrowserStack: agent runtime or device lab?](https://mobilebox.dev/blog/mobilebox-vs-browserstack?via=llms): Compare an agent-facing Android sandbox with a real-device Appium testing workflow, using documented responsibilities instead of rankings.
- [Mobilebox or Genymotion: compare the Android control surface](https://mobilebox.dev/blog/mobilebox-vs-genymotion?via=llms): Compare device provisioning, ADB-based toolchains, agent actions and the exact persistence semantics of your chosen Android workflow.
- [Give each agent a key. Keep the workspace boundary clear.](https://mobilebox.dev/blog/android-api-key-security?via=llms): Understand project-wide API-key access, browser sessions, safe rotation and the difference between a named key and an isolated project.
- [Treat Android permission dialogs as part of the test](https://mobilebox.dev/blog/android-permission-dialogs?via=llms): Handle real consent and denial screens, choose runtime permission pre-grants deliberately and keep special permissions separate.
- [Will this Android app work on a cloud phone?](https://mobilebox.dev/blog/android-app-compatibility?via=llms): Check APK architecture, exposed UI, device services, physical features and attestation before promising a particular app workflow.
- [Fresh install, app restart, park or delete? Choose the right reset.](https://mobilebox.dev/blog/fresh-vs-persistent-sandboxes?via=llms): Distinguish process state, saved app data, installed packages and remote records before resetting or retaining an Android sandbox.
- [How to evaluate an Android agent without grading its own story](https://mobilebox.dev/blog/android-agent-evaluations?via=llms): Define testable outcomes, separate environment and control failures, include recovery cases and retain evidence for every attempt.
- [A timeout does not mean the tap never happened](https://mobilebox.dev/blog/retry-mobile-actions-safely?via=llms): Reconcile phone creation, inspect partial action batches and check side effects before retrying an uncertain Android operation.
- [The locale changed. Why is the app still in English?](https://mobilebox.dev/blog/debug-android-localization?via=llms): Debug system locale, per-app language, installed translations, server content and timezone as separate inputs to a localization test.
- [What leaves the phone when your agent reads the screen?](https://mobilebox.dev/blog/android-agent-data-boundaries?via=llms): Map credentials, model inputs, screenshots, traces and CI artifacts so the evidence you keep matches the task you need to judge.
- [Test your Android app with Claude Code on a cloud phone](https://mobilebox.dev/blog/claude-code-android-app-testing?via=llms): Give Claude Code a hosted Android phone over MCP, install your APK from a URL, check the first screen and delete the phone, with the tool calls we ran.
- [No KVM in CI? Run the APK on a remote Android phone](https://mobilebox.dev/blog/android-emulator-without-kvm?via=llms): Why the Android emulator stalls without KVM, three ways around it, and a tested curl script that installs an APK on a cloud phone from any runner.
- [Cloud Android phones for AI agents, compared](https://mobilebox.dev/blog/cloud-android-for-ai-agents-compared?via=llms): Mobilebox, Mobilerun, Limrun, phonebox.dev, Clousd and Ramus side by side: phone type, MCP endpoint, sign-in, published price and what a stopped phone keeps.
- [Android MCP server: hosted or local?](https://mobilebox.dev/blog/android-mcp-server-hosted-vs-local?via=llms): Local servers like mobile-mcp drive your own emulator over ADB; hosted servers give your agent a URL and a phone. Endpoints, sign-in and a tools/list you can run.
- [iOS testing for AI coding agents: what runs where today](https://mobilebox.dev/blog/ios-testing-for-ai-coding-agents?via=llms): Every iOS path for an agent runs on a Mac: Simulator, XCUITest, mobile-mcp, macOS CI runners and device farms, and where Mobilebox iPhone sandboxes fit.
- [Real Android devices or cloud phones for your agent?](https://mobilebox.dev/blog/real-android-devices-vs-cloud-phones?via=llms): Use a cloud Android phone for UI tasks and a physical device for attestation, hardware and performance. What each covers, and how Mobilebox sets up real devices.
- [Your agent built an iPhone app. How do you test it?](https://mobilebox.dev/blog/test-iphone-apps-your-agent-built?via=llms): Simulator first, an outcome-based XCUITest second, a real iPhone third, then a device lab: a Mac-based checklist for iPhone apps an AI agent wrote.
- [Mobilebox or Firebase Test Lab for Android testing?](https://mobilebox.dev/blog/mobilebox-vs-firebase-test-lab?via=llms): Firebase Test Lab runs your test suites across a device matrix; Mobilebox gives your agent a phone it drives step by step. What each does, what it costs, when to use both.
- [Cloud phone or a local Android emulator for your agent?](https://mobilebox.dev/blog/mobilebox-vs-local-emulator?via=llms): A local emulator is free when your machine has hardware acceleration and a screen. Cloud agents, CI without KVM, many phones at once and kept logins need a cloud phone.
- [Mobilebox, Limrun or Mobilerun: which fits your agent?](https://mobilebox.dev/blog/mobilebox-vs-limrun?via=llms): Limrun builds and runs apps on cloud iOS and Android simulators, Mobilerun sells plans, hosted phones and its own agent, Mobilebox gives your agent phones over REST and MCP.
- [How do I give Cursor, Codex or VS Code an Android phone?](https://mobilebox.dev/blog/android-mcp-cursor-codex-vscode?via=llms): One remote MCP server for all three: the exact Cursor mcp.json, Codex config.toml and VS Code mcp.json entries, with the key read from your environment.
- [Can my agent run 50 phones in parallel?](https://mobilebox.dev/blog/run-android-phones-in-parallel?via=llms): Create one phone per task with one call each, give each an idempotency key, run the agents side by side and park or delete every phone in finally. What 50 phones cost.
- [Can each phone get its own residential IP?](https://mobilebox.dev/blog/residential-ip-per-phone?via=llms): Ask for network residential or mobile and a city: the phone keeps its IP, and its GPS, timezone and locale match the city. Prices per GB, your own proxy, and the rules.
- [What does Mobilebox cost for a team?](https://mobilebox.dev/blog/mobilebox-pricing-for-teams?via=llms): The same per-minute prices for one developer or fifty: a key per agent, parked phones free, dedicated devices from $79 a month and volume pricing past 100 devices.
- [How fast do cloud Android phones for agents start? (Nov 2026 benchmark)](https://mobilebox.dev/blog/cloud-android-start-time-benchmark?via=llms): Measured on free tiers: Limrun 0.98 s, Mobilebox 19.4 s and Phone Harness 23 s from create to first screenshot, plus tap latency, APK install, 10-minute cost and park/resume.
- [Android emulator on CI without KVM vs a cloud phone: timings](https://mobilebox.dev/blog/android-emulator-ci-vs-cloud-phone?via=llms): One GitHub Actions run: the emulator with KVM, without KVM and a cloud phone from the same runner, timed from launch to first screenshot, tap and APK install.
- [Agent sandboxes compared: start time and price](https://mobilebox.dev/blog/agent-sandbox-start-times?via=llms): Code and browser sandboxes start in about a second or less, cloud Android phones in 1 to 23 seconds. Published and measured start times with per-minute prices.
- [What is a cloud phone for AI agents?](https://mobilebox.dev/blog/what-is-a-cloud-phone-for-ai-agents?via=llms): A phone in a data center that your agent drives over an API or MCP. How it differs from a device farm and a multi-account phone, and five questions to choose one.
- [Best Android MCP servers (2026)](https://mobilebox.dev/blog/best-android-mcp-servers?via=llms): mobile-mcp, Limrun, Phone Harness, Mobilerun, phonebox.dev, Mobilebox, Appium MCP, BrowserStack and more: where the phone runs, how agents connect, price as published and measured start times.
- [Best cloud phones for AI agents (2026)](https://mobilebox.dev/blog/best-cloud-phones-for-ai-agents?via=llms): Limrun, Phone Harness, Mobilerun, phonebox.dev, Mobilebox, Clousd and Ramus, plus device farms: what each phone is, what it costs, what a stopped phone keeps, measured start times.
- [Gemini CLI on Android: add a cloud phone over MCP](https://mobilebox.dev/blog/gemini-cli-android-mcp?via=llms): The exact ~/.gemini/settings.json entry and gemini mcp add command for the Mobilebox MCP server, OAuth with /mcp auth, trusted folders, a first prompt and what a run costs.
- [Windsurf on Android: a cloud phone for Cascade over MCP](https://mobilebox.dev/blog/windsurf-android-mcp?via=llms): The mcp_config.json entry with serverUrl and an env-read key, OAuth for Cascade, where the file lives now that Windsurf is Devin Desktop, a first prompt and its cost.
- [Cline on Android: give Cline a cloud phone over MCP](https://mobilebox.dev/blog/cline-android-mcp?via=llms): Add Mobilebox in Cline’s Remote Servers tab or its MCP settings JSON with type streamableHttp, or from the Cline CLI; a first prompt, auto-approve and what a run costs.
- [GitHub Copilot on Android: a cloud phone in agent mode](https://mobilebox.dev/blog/github-copilot-android-mcp?via=llms): One-click install and OAuth in VS Code, the ~/.copilot/mcp-config.json entry with an env-read key, a team .vscode/mcp.json without secrets, a first prompt and its cost.
- [What is the cheapest cloud Android phone for AI agents per minute?](https://mobilebox.dev/blog/cheapest-cloud-android-phone-per-minute?via=llms): Clousd $0.004, Mobilebox $0.01, Mobilerun $0.03, Limrun $0.04, Phone Harness 5¢, phonebox.dev and Genymotion $0.06 a minute as published, plus what a measured 10-minute session cost.
- [An Android phone for your Python AI agent](https://mobilebox.dev/blog/android-phone-for-python-ai-agent?via=llms): pip install mobilebox, then one cloud phone per pull request: start it, install the build, walk the flow, screenshot each step, delete it. A tested script, the LangGraph version and what a run costs.

## Markdown versions
Every public page is also served as Markdown at its path + `.md`, with the same text as the page.
- [About Mobilebox: mobile sandboxes for AI agents, contact and support](https://mobilebox.dev/about.md?via=llms)
- [AI sandbox for agents: code, browser or phone?](https://mobilebox.dev/ai-sandbox.md?via=llms)
- [Android MCP server for Claude Code, Cursor and any MCP client](https://mobilebox.dev/android-mcp-server.md?via=llms)
- [App automation with AI agents: test your app, run your tasks](https://mobilebox.dev/app-automation.md?via=llms)
- [Cloud Android for AI agents: start-time benchmark (Nov 2026)](https://mobilebox.dev/benchmarks.md?via=llms)
- [Imprint](https://mobilebox.dev/imprint.md?via=llms)
- [Mobilebox · Mobile sandboxes for your AI agents: Android and iPhone over API and MCP](https://mobilebox.dev/index.md?via=llms)
- [iOS sandbox for AI agents: iPhone and iPad](https://mobilebox.dev/ios.md?via=llms)
- [Live view: watch your AI agent use a phone, live](https://mobilebox.dev/live-view.md?via=llms)
- [Mobile sandbox for AI agents: cloud phones over API and MCP](https://mobilebox.dev/mobile-sandbox.md?via=llms)
- [Phone agent: give your AI agent a phone it can use](https://mobilebox.dev/phone-agent.md?via=llms)
- [Pricing](https://mobilebox.dev/pricing.md?via=llms)
- [Privacy](https://mobilebox.dev/privacy.md?via=llms)
- [Real device cloud for AI agents: physical Android phones](https://mobilebox.dev/real-devices.md?via=llms)
- [Terms](https://mobilebox.dev/terms.md?via=llms)
- [Changelog: what shipped in Mobilebox](https://mobilebox.dev/changelog.md?via=llms)
- [Quickstart: an Android phone for your AI agent](https://mobilebox.dev/docs/index.md?via=llms)
- [Agent guide: observe, act, verify, park](https://mobilebox.dev/docs/agents.md?via=llms)
- [API reference: REST and MCP for phones](https://mobilebox.dev/docs/reference.md?via=llms)
- [Errors and recovery for phone agents](https://mobilebox.dev/docs/errors.md?via=llms)
- [Integrations: Android phones for OpenAI Agents SDK, LangGraph, CrewAI and more](https://mobilebox.dev/integrations.md?via=llms)
- [OpenAI Agents SDK on Android: mobile app automation over MCP](https://mobilebox.dev/integrations/openai-agents.md?via=llms)
- [LangGraph mobile app automation: an Android phone with langchain-mobilebox](https://mobilebox.dev/integrations/langgraph.md?via=llms)
- [CrewAI mobile app automation: an Android phone over MCP](https://mobilebox.dev/integrations/crewai.md?via=llms)
- [browser-use on Android: one agent for the web and mobile apps](https://mobilebox.dev/integrations/browser-use.md?via=llms)
- [Mastra MCP on Android: mobile app automation for Mastra agents](https://mobilebox.dev/integrations/mastra.md?via=llms)
- [Vercel AI SDK MCP on Android: mobile app automation in TypeScript](https://mobilebox.dev/integrations/vercel-ai-sdk.md?via=llms)
- [Claude Agent SDK on Android: MCP phone tools for Claude](https://mobilebox.dev/integrations/claude-agent-sdk.md?via=llms)
- [Journal: guides for AI agents on phones](https://mobilebox.dev/blog.md?via=llms)
- [Give your coding agent an Android sandbox over MCP](https://mobilebox.dev/blog/android-agent-mcp.md?via=llms)
- [Does this task need a phone or a browser?](https://mobilebox.dev/blog/native-app-or-browser.md?via=llms)
- [Mobilebox or Mobilerun: where do the agent and the phone run?](https://mobilebox.dev/blog/mobilebox-vs-mobilerun.md?via=llms)
- [Mobilebox or Appium for Android automation?](https://mobilebox.dev/blog/mobilebox-vs-appium.md?via=llms)
- [Android, E2B, Browserbase: which sandbox fits?](https://mobilebox.dev/blog/android-vs-agent-sandboxes.md?via=llms)
- [Why your agent tapped the wrong thing](https://mobilebox.dev/blog/screen-refs-and-recovery.md?via=llms)
- [Batch the steps you know. Observe the ones you don’t.](https://mobilebox.dev/blog/batch-android-actions.md?via=llms)
- [Install APKs and split bundles over an API](https://mobilebox.dev/blog/install-apk-split-bundles.md?via=llms)
- [Keep the login. Stop the running phone.](https://mobilebox.dev/blog/park-resume-android.md?via=llms)
- [Put a budget around your Android agent](https://mobilebox.dev/blog/android-sandbox-costs.md?via=llms)
- [Timezone, locale, GPS and IP are four different inputs](https://mobilebox.dev/blog/locale-location-proxy.md?via=llms)
- [A successful tap is not a successful task](https://mobilebox.dev/blog/verify-agent-workflows.md?via=llms)
- [Screenshot or accessibility tree? Choose the evidence your agent needs](https://mobilebox.dev/blog/screenshot-vs-accessibility-tree.md?via=llms)
- [Run an APK smoke test from CI without a local emulator](https://mobilebox.dev/blog/android-apk-ci-smoke-tests.md?via=llms)
- [Mobilebox or BrowserStack: agent runtime or device lab?](https://mobilebox.dev/blog/mobilebox-vs-browserstack.md?via=llms)
- [Mobilebox or Genymotion: compare the Android control surface](https://mobilebox.dev/blog/mobilebox-vs-genymotion.md?via=llms)
- [Give each agent a key. Keep the workspace boundary clear.](https://mobilebox.dev/blog/android-api-key-security.md?via=llms)
- [Treat Android permission dialogs as part of the test](https://mobilebox.dev/blog/android-permission-dialogs.md?via=llms)
- [Will this Android app work on a cloud phone?](https://mobilebox.dev/blog/android-app-compatibility.md?via=llms)
- [Fresh install, app restart, park or delete? Choose the right reset.](https://mobilebox.dev/blog/fresh-vs-persistent-sandboxes.md?via=llms)
- [How to evaluate an Android agent without grading its own story](https://mobilebox.dev/blog/android-agent-evaluations.md?via=llms)
- [A timeout does not mean the tap never happened](https://mobilebox.dev/blog/retry-mobile-actions-safely.md?via=llms)
- [The locale changed. Why is the app still in English?](https://mobilebox.dev/blog/debug-android-localization.md?via=llms)
- [What leaves the phone when your agent reads the screen?](https://mobilebox.dev/blog/android-agent-data-boundaries.md?via=llms)
- [Test your Android app with Claude Code on a cloud phone](https://mobilebox.dev/blog/claude-code-android-app-testing.md?via=llms)
- [No KVM in CI? Run the APK on a remote Android phone](https://mobilebox.dev/blog/android-emulator-without-kvm.md?via=llms)
- [Cloud Android phones for AI agents, compared](https://mobilebox.dev/blog/cloud-android-for-ai-agents-compared.md?via=llms)
- [Android MCP server: hosted or local?](https://mobilebox.dev/blog/android-mcp-server-hosted-vs-local.md?via=llms)
- [iOS testing for AI coding agents: what runs where today](https://mobilebox.dev/blog/ios-testing-for-ai-coding-agents.md?via=llms)
- [Real Android devices or cloud phones for your agent?](https://mobilebox.dev/blog/real-android-devices-vs-cloud-phones.md?via=llms)
- [Your agent built an iPhone app. How do you test it?](https://mobilebox.dev/blog/test-iphone-apps-your-agent-built.md?via=llms)
- [Mobilebox or Firebase Test Lab for Android testing?](https://mobilebox.dev/blog/mobilebox-vs-firebase-test-lab.md?via=llms)
- [Cloud phone or a local Android emulator for your agent?](https://mobilebox.dev/blog/mobilebox-vs-local-emulator.md?via=llms)
- [Mobilebox, Limrun or Mobilerun: which fits your agent?](https://mobilebox.dev/blog/mobilebox-vs-limrun.md?via=llms)
- [How do I give Cursor, Codex or VS Code an Android phone?](https://mobilebox.dev/blog/android-mcp-cursor-codex-vscode.md?via=llms)
- [Can my agent run 50 phones in parallel?](https://mobilebox.dev/blog/run-android-phones-in-parallel.md?via=llms)
- [Can each phone get its own residential IP?](https://mobilebox.dev/blog/residential-ip-per-phone.md?via=llms)
- [What does Mobilebox cost for a team?](https://mobilebox.dev/blog/mobilebox-pricing-for-teams.md?via=llms)
- [How fast do cloud Android phones for agents start? (Nov 2026 benchmark)](https://mobilebox.dev/blog/cloud-android-start-time-benchmark.md?via=llms)
- [Android emulator on CI without KVM vs a cloud phone: timings](https://mobilebox.dev/blog/android-emulator-ci-vs-cloud-phone.md?via=llms)
- [Agent sandboxes compared: start time and price](https://mobilebox.dev/blog/agent-sandbox-start-times.md?via=llms)
- [What is a cloud phone for AI agents?](https://mobilebox.dev/blog/what-is-a-cloud-phone-for-ai-agents.md?via=llms)
- [Best Android MCP servers (2026)](https://mobilebox.dev/blog/best-android-mcp-servers.md?via=llms)
- [Best cloud phones for AI agents (2026)](https://mobilebox.dev/blog/best-cloud-phones-for-ai-agents.md?via=llms)
- [Gemini CLI on Android: add a cloud phone over MCP](https://mobilebox.dev/blog/gemini-cli-android-mcp.md?via=llms)
- [Windsurf on Android: a cloud phone for Cascade over MCP](https://mobilebox.dev/blog/windsurf-android-mcp.md?via=llms)
- [Cline on Android: give Cline a cloud phone over MCP](https://mobilebox.dev/blog/cline-android-mcp.md?via=llms)
- [GitHub Copilot on Android: a cloud phone in agent mode](https://mobilebox.dev/blog/github-copilot-android-mcp.md?via=llms)
- [What is the cheapest cloud Android phone for AI agents per minute?](https://mobilebox.dev/blog/cheapest-cloud-android-phone-per-minute.md?via=llms)
- [An Android phone for your Python AI agent](https://mobilebox.dev/blog/android-phone-for-python-ai-agent.md?via=llms)