ghost-in-the-droid (ghost-in-the-droid/android-agent) is an MCP server listed on the M8ven Trust Index. It scores 89 out of 100, grade B. It declares 66 tools. No publisher has claimed this listing.

B
Emerging
89/100
8 days ago

ghost-in-the-droid

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

ghost-in-the-droid

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 5 credentials: ANTHROPIC_API_KEY, OPENROUTER_API_KEY, OPENAI_API_KEY, GITD_VLLM_API_KEY, GITHUB_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configBASE_URL
configGITD_CORS_ORIGINS
configGHOST_HOME_OVERRIDE
configIOS_DEVICE_UDIDiPhone or simulator UDID; devices are addressed as ios:<udid>
configIOS_BUNDLE_IDDefault iOS app/browser bundle, e.g. com.google.chrome.ios or com.apple.mobilesafari
configIOS_BROWSER_NAME
configANDROID_SERIAL
configGHOST_CONFIG_DIR
configOLLAMA_BASE_URL
configGHOST_BACKEND
configGHOST_MODEL
🔐 secretANTHROPIC_API_KEYAlternative LLM provider
🔐 secretOPENROUTER_API_KEYOpenRouter LLM provider
🔐 secretOPENAI_API_KEYLLM features (Skill Creator, Agent Chat)
configGHOST_MODE
configIOS_STREAM_FORCE_LOCALHOST
🔐 secretGITD_VLLM_API_KEY
configGITD_VLLM_BASE_URL
configGHOST_REMOTE_HOST
configSUB_AGENT_MODEL
🔐 secretGITHUB_TOKEN
configGHOST_DEVICE
configDEVICE
configGITD_ENABLE_IOSiOS is opt-in: enable it with =1 (or ios_platform_enabled=true
configIOS_DEVICES_JSONPer-device iOS config for multiple phones/simulators, WDA ports, bundle IDs, and MJPEG ports
configIOS_CONFIG_FILE
configIOS_REMOTE_XPC_REGISTRY_PORTS
configIOS_REMOTE_XPC_REGISTRY_PORT
configIOS_REMOTE_XPC_TUNNEL_START_TIMEOUT
configIOS_APPIUM_COMMAND
configIOS_DEVICE_UDIDS
configIOS_WDA_DIRECT
configIOS_REMOTEXPC_REGISTRY
configIOS_WAIT_FOR_QUIESCENCE
configIOS_LAUNCH_BUNDLE_ON_SESSION
configIOS_APPLY_WDA_SETTINGS
configIOS_APPIUM_LOG
configIOS_REMOTE_XPC_TUNNEL_LOG
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

66/66 tools missing one or more hints — list_devices (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); screenshot (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_elements (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +63 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 2 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/ghost-in-the-droid/android-agent)](https://m8ven.ai/mcp/ghost-in-the-droid/android-agent)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: 7c09f6cd14b6f9890517f2bbf19fb92f0970f8fc
code hash: bf256af1ca48dbaea75462d73b4a01f14bc2c08ec5d4c8d66610b566cd7a3f64
verified: 9/2/2026, 8:01:57 PM
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client