benchfleet-mcp
Allows AI agents to safely interact with real Android phones through BenchFleet, including listing devices, viewing screens, reading UI elements, tapping, typing, launching apps, running workflows, taking screenshots, and managing device tasks with permission controls and audit logging.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@benchfleet-mcpopen Settings on the demo phone and tell me what's on the screen"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
benchfleet-mcp
Let AI agents use your real Android phones, safely. benchfleet-mcp connects Claude Code, Codex, Cursor, Claude
Desktop and any other MCP client to BenchFleet, the
self-hosted control hub for real Android phones. The agent can list your phones, look at their screens, read the
elements on them, tap, type, open apps and run your published workflows — only on the phones and with the actions
you allow, with approvals for anything sensitive and every step in BenchFleet's audit log.
It is a thin connector: it forwards MCP messages to the BenchFleet app running on the same computer and reaches nothing else. The tools, the permissions and the phones are all in the app.
Set up
Install BenchFleet from https://benchfleet.com/download and connect your phones (or use its demo phones).
In BenchFleet: Settings → AI clients → Connect an AI client…, choose what the client may do (Look only, Look and operate, or chosen capabilities) and on which phones, and copy the token it shows once.
Add the server to your client:
Claude Code
claude mcp add benchfleet --env BENCHFLEET_TOKEN=<token> -- npx -y benchfleet-mcpCodex (
~/.codex/config.toml)[mcp_servers.benchfleet] command = "npx" args = ["-y", "benchfleet-mcp"] env = { BENCHFLEET_TOKEN = "<token>" }Claude Desktop, Cursor and other clients (
mcpServers){ "mcpServers": { "benchfleet": { "command": "npx", "args": ["-y", "benchfleet-mcp"], "env": { "BENCHFLEET_TOKEN": "<token>" } } } }
The app must be running. Disconnect in BenchFleet stops the token at once.
Related MCP server: Karagöz
Tools
list_devices, get_device, get_screen, get_ui_tree, find_element, read_text, wait_for, tap_element,
long_press_element, type_text, type_secret (a password from BenchFleet's vault, never its value), swipe,
scroll_to, press_key, launch_app, stop_app, take_screenshot, get_device_logs, list_workflows,
run_workflow, queue_task (a workflow, or a goal in plain words for the phones' AI agents), get_task_status,
pause_device, resume_device, request_manual_control. A client sees only the tools its access allows. There is
no shell, file transfer or install tool. A phone a person is controlling, a paused phone and a phone without
Automation allowed refuse every action; CAPTCHAs and other human-only checks stop the agent and ask a person.
Settings
Variable | Meaning |
| Required: the client's token from the app ( |
| Optional: the app's address, when it is not found in its data folder |
| Optional: the app's data folder, when it is not the default one |
Plans: AI clients need BenchFleet Pro or Team (https://benchfleet.com/pricing); the personal edition has no limits. Support: support@benchfleet.com.
Use it in Claude Code as a plugin
/plugin marketplace add benchfleet/benchfleet-mcp
/plugin install benchfleet@benchfleet-pluginsSet BENCHFLEET_TOKEN in your environment first (the token from BenchFleet: Settings → AI clients).
Use it in Gemini CLI
gemini extensions install https://github.com/benchfleet/benchfleet-mcpThis server cannot be deployed
Maintenance
Related MCP Connectors
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
Cloud Android phones for AI agents: create a phone, read the screen, tap, type, install APKs, park.
Disposable cloud Android emulators for coding agents: run an APK or PR build, tap, type, screenshot.
A real Android phone in the cloud for MCP agents: observe the screen, act, reset to a saved state.
Related MCP Servers
- FlicenseNot gradedqualityBmaintenanceEnables an agent to control a real Android phone by reading structured UI elements and performing actions such as tapping, swiping, typing, and extracting fields from known app screens.1-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to automate Android and iOS devices, including emulators and physical devices, by capturing screenshots, reading UI accessibility trees, performing touch and text input, and managing app lifecycle and logs.MIT
- AlicenseNot gradedqualityAmaintenanceEnables AI agents to operate a real Android phone through its accessibility service, exposing screen trees with stable refs, taps, typing, gestures, notifications, apps, and other device controls.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to control real cloud phones by reading screens as text, tapping, typing, installing APKs, handing off to humans, and parking devices to stop billing, without ADB or emulators.MIT