Droidsight MCP Server - install, status & alternatives [2026]

01 · Install Droidsight

before you install - you'll need

Set DROIDSIGHT_DEVICE_SERIAL before connecting.

Claude Code

claude mcp add edgecasehuman-droidsight -- npx -y @edgecasehuman/droidsight

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "edgecasehuman-droidsight": {
      "command": "npx",
      "args": [
        "-y",
        "@edgecasehuman/droidsight"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repo age created 2026-07-26 - young repo, little track record yet

license MIT - declared in the repository

npm package @edgecasehuman/droidsight - published under the repo owner's npm scope (@edgecasehuman)

registry namespace io.github.edgecasehuman is GitHub-verified and matches the repo owner

03 · What Droidsight can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can start, stop, or read the background H.264 stream, scan for text and tap it the instant it appears, retrying until timeout. Avoids the miss between a screenshot and a tap, run a bounded, fully prevalidated sequence of safe actions, and open a URL.

The 31 tools it gives your agent

Extracted from the project's README - what droidsight lets an agent do.

mcp_android_vision_query: - Screenshot, hierarchy, OCR, and element or template search. Its elements and tap_element actions avoid coordinate arithmetic entirely.
mcp_android_vision_stream: - Start, stop, or read the background H.264 stream.
mcp_android_get_view_hierarchy: - The accessibility tree as structured JSON.
mcp_android_smart_wait: - Block until an element appears, or time out.
mcp_android_input_act: - Tap, type, key events, swipe, smart tap, and IME control.
mcp_android_tap_text: - Scan for text and tap it the instant it appears, retrying until timeout. Avoids the miss between a screenshot and a tap.
mcp_android_run_flow: - Run a bounded, fully prevalidated sequence of safe actions.
mcp_android_record_gesture: - Record raw touch input for a fixed duration.
mcp_android_play_gesture: - Replay a recorded gesture timeline.
mcp_android_app_manage: - Launch, stop, list, install, and read crash logs. Uninstall, clear data, permission, enable, and disable additionally require confirm_destructive.
mcp_android_app_instrumentation: - Deep state inspection: activity, window, process list, stack traces.
mcp_android_open_url: - Open a URL.

show all 31 tools

mcp_android_start_intent: - Start an arbitrary intent.
mcp_android_device_control: - Clipboard, battery, device info, lock state, unlock, rotation.
mcp_android_system_control: - Accessibility services and the draw-over-other-apps permission. Grants screen-read and input-injection authority across every app.
mcp_android_network_control: - Wi-Fi, mobile data, HTTP proxy, phone calls, SMS, wireless ADB pairing.
mcp_android_sensor_control: - Mock battery level and charging status; GPS mocking is emulator-only.
mcp_android_check_health: - Connectivity and responsiveness of the selected device.
mcp_android_check_debug_exposure: - Report which developer settings are enabled and therefore visible to apps.
mcp_android_diagnostic_stream: - Read logcat, clear it, or read buffered raw and semantic events.
mcp_android_read_recent_events: - Buffered device events from the optional monitor.
mcp_android_log_filter: - Filter logs by regex, tag, or priority.
mcp_android_get_notifications: - Dump posted notifications, including unredacted message content.
mcp_android_file_system: - List, read, push, and pull files, confined to DROIDSIGHT_LOCAL_ROOT.
mcp_android_forensics_control: - Query an on-device SQLite database, hash a file, or irreversibly delete an application's data.
mcp_android_start_recording: - Begin a screen recording, up to 180 seconds, written to the device.
mcp_android_stop_recording: - Stop it. The file stays on the device.
mcp_android_companion: - Post a notification, show a transient message, or open a URL for whoever is holding the phone.
mcp_android_sentinel_control: - Register a watched package. See Background enforcement before using it.
mcp_android_run_shell: - Run an arbitrary device shell command. No filtering of any kind.
mcp_android_run_macro: - Run up to 100 shell commands in sequence, stopping at the first failure.

Latest releases

v1.0.0 · 2026-08-12

Bump actions/download-artifact from 4.3.0 to 8.0.1 · Bump actions/checkout from 4.4.0 to 7.0.1 · Bump actions/upload-artifact from 4.6.2 to 7.0.1 · Bump base64 from 0.21.7 to 0.23.0 · Bump rand from 0.9.5 to 0.10.2…

04 · Who maintains Droidsight

droidsight is maintained by edgecasehuman. It's the only MCP server we track from this author; the repo dates to Jul 2026.

05 · Facts

repository: github.com/edgecasehuman/droidsight
category: browser automation - ranked #137 of 255 actively-maintained browser automation servers as of 2026-09-18.
release cadence: 1 release in the last 90 days (latest 2026-08-12)
registry: io.github.edgecasehuman/droidsight (active, first published 2026-08-12)
packages: npm:@edgecasehuman/droidsight

06 · Droidsight FAQ

Is Droidsight still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-13 and it shipped 1 release in the last 90 days. We re-verify nightly.

What can Droidsight do?

With this server connected, an agent can start, stop, or read the background H.264 stream, scan for text and tap it the instant it appears, retrying until timeout. Avoids the miss between a screenshot and a tap, run a bounded, fully prevalidated sequence of safe actions, and open a URL.

How do I install Droidsight?

Run `npx -y @edgecasehuman/droidsight`. The README documents one environment variable (DROIDSIGHT_DEVICE_SERIAL) to set first. Set DROIDSIGHT_DEVICE_SERIAL before connecting. You can also paste the ready-made client config above.

Does Droidsight run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Droidsight

Alternatives to Droidsight

Maintained browser automation servers if Droidsight isn't the fit.

Pairs well with

Servers that cover what Droidsight doesn't - only shown when the pairing reason fits the companion.

More browser automation MCP servers · Electron Stagewright MCP Server · ellmos Blender Use · Pagerunner - The Browser Layer That Learns · Parallel Browser MCP · Extentos MCP Server

More Rust MCP servers · Zzop · Calm MCP · Altium Designer MCP · Vision Squeezer · see all