Enables wireless screenshot capture from Android devices over WiFi for UI debugging and visual inspection during development, with automatic device detection and connection capabilities.
Click on "Install 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., "@Android Screenshot MCP Server screenshot my Android phone"
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.
MCP server for taking screenshots of Android devices over WiFi. Useful for UI debugging and visual inspection during development.
Wireless screenshot capture via ADB
Automatic device detection and connection
Smart pairing for first-time setup
UI/UX debugging and layout inspection
Related MCP server: Android MCP Server
Install dependencies:
npm installAdd to Claude Code:
claude mcp add android /path/to/android-screenshot-mcp/src/index.jsEnable wireless debugging on your Android device:
Settings → Developer Options → Wireless Debugging
Note the IP address and ports shown
The tool automatically detects connected devices. If no device is connected, it will guide you through the setup.
For already connected devices:
screenshot phoneFor new connections, provide the IP and port shown in your device's wireless debugging settings:
screenshot phone with 192.168.1.100:41737If this is your first time connecting, you'll need to pair first:
screenshot phone with 192.168.1.100:41737 and pairing code 123456 port 54321The tool accepts several formats:
deviceIP: "192.168.1.100:41737" - IP with port included
deviceIP: "192.168.1.100", debugPort: 41737 - Separate parameters
Natural language like "192.168.1.100:41737 and pairing: 123456 port 54321"
Android 11+ device with wireless debugging
ADB installed on your computer
Same WiFi network for both devices
This error has been fixed in the latest version. If you still encounter it, ensure you're running the latest code.
Verify wireless debugging is enabled on your device
Check that the IP address and port match what's shown on your device
Make sure both devices are on the same WiFi network
Try disabling and re-enabling wireless debugging
Note: The wireless debugging port changes when you toggle it off/on
Pairing codes expire quickly (usually within 2 minutes)
Generate a fresh pairing code right before using it
The pairing port is different from the wireless debugging port
Once paired, you shouldn't need to pair again unless you reset connections
The tool uses wireless ADB connections and remembers your last successful connection for convenience. Each screenshot session will:
Check for already connected devices first
If none found, try to reconnect to the last used device automatically
If that fails, prompt for connection details
Successfully connected devices are saved to ~/.android-screenshot-mcp/config.json
This means after your first successful connection, the tool can often reconnect automatically without needing the IP and port again.
Connect to an Android device and take a screenshot. Use when no device is connected.
| Name | Required | Description | Default |
|---|---|---|---|
| deviceIP | Yes | IP address of the Android device. Can include port like "192.168.1.100:12345" | |
| debugPort | No | Wireless debugging port (different from pairing port) | |
| pairingPort | No | Pairing port shown on device for initial pairing | |
| pairingCode | No | Pairing code shown on device for initial pairing | |
| outputPath | No | Path where to save the screenshot (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions connecting and taking a screenshot but doesn't describe what happens during connection (e.g., pairing process, authentication needs, potential errors), the screenshot format, or any rate limits. For a tool with multiple parameters and no annotations, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core action and followed by usage guidance. Every sentence earns its place with no wasted words, making it highly efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (5 parameters, no output schema, no annotations), the description is somewhat complete but lacks details on behavioral aspects like connection process and screenshot output. It covers purpose and usage well but doesn't fully compensate for the missing annotations and output schema, leaving gaps for an AI agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description doesn't add any meaning beyond what the schema provides, such as explaining how parameters interact (e.g., pairingPort and pairingCode are needed together). Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Connect to an Android device and take a screenshot') and resource ('Android device'), making the purpose explicit. However, it doesn't distinguish this from the sibling 'screenshot' tool, which might handle already-connected devices, so it misses full sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool ('Use when no device is connected'), which clearly distinguishes it from the sibling 'screenshot' tool that likely handles connected devices. This gives clear context and alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Take a screenshot of any connected Android device. Uses existing ADB connections or connects wirelessly if device info provided.
| Name | Required | Description | Default |
|---|---|---|---|
| deviceIP | No | IP address of the Android device. Can include port like "192.168.1.100:12345" | |
| debugPort | No | Wireless debugging port (different from pairing port) | |
| pairingPort | No | Pairing port shown on device for initial pairing | |
| pairingCode | No | Pairing code shown on device for initial pairing | |
| outputPath | No | Path where to save the screenshot (optional) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the connection behavior (uses existing ADB or wireless with device info) and implies a write operation (saving a screenshot), but doesn't mention authentication requirements, rate limits, error conditions, or what happens if no outputPath is specified. It adds some context but leaves significant gaps for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise with two sentences that each earn their place: the first states the core purpose, the second explains the connection behavior. No wasted words, well-structured and front-loaded with the main action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description provides adequate purpose and connection context but lacks details about the screenshot format, error handling, authentication needs, or what happens when parameters are omitted. Given the complexity of device interaction and 5 parameters, more behavioral context would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already fully documents all 5 parameters. The description adds no specific parameter information beyond what's in the schema, though it implies the optional nature of parameters by stating 'if device info provided' and marking outputPath as optional. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Take a screenshot') and target resource ('any connected Android device'), distinguishing it from the sibling 'connect_and_screenshot' by emphasizing it uses existing connections or wireless setup rather than establishing a new connection as part of the operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context on when to use this tool: for taking screenshots on Android devices with existing ADB connections or wireless connections if device info is provided. It distinguishes from 'connect_and_screenshot' by implying this tool doesn't handle connection establishment, but doesn't explicitly state when not to use it or name alternatives beyond the sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
connect_and_screenshotscreenshotScored across 2 tools
The two tools have overlapping purposes with unclear boundaries. Both are focused on taking Android screenshots, with 'connect_and_screenshot' implying connection and capture, while 'screenshot' can also handle connections if needed. This creates ambiguity about when to use each tool, as their descriptions suggest similar functionality with minor variations in connection handling.
The tool names follow a consistent snake_case pattern and use clear verbs ('connect_and_screenshot', 'screenshot'). While the naming is technically consistent, the inclusion of 'connect_and_' in one name versus not in the other creates a minor deviation in structure, but overall the naming is readable and follows a predictable style.
With only 2 tools, the server feels thin for its purpose of Android screenshot management. While it covers basic screenshot functionality, the limited tool count may restrict more advanced operations or device management tasks, placing it in the borderline range where the scope seems underdeveloped.
The tool set is significantly incomplete for Android device interaction. It only provides screenshot capabilities without covering essential operations like listing devices, managing connections, handling multiple devices, or performing other common ADB commands. This creates gaps that could lead to agent failures when broader device control is needed.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Drive real devices from your AI Coding tool. Embed a client SDK (Unity, Godot, Flutter, iOS/macOS, Android, React Native, Web) in your app, then capture screenshots, traverse the UI tree, inject taps and key events, and run automated test tasks on the physical device over a secure relay.
remote debug iOS/Android/Unity/Godot/Flutter/RN/Web on real-device.ui-tree/screenshots/taps,tests.
Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any PC.
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
