Specter MCP
Enables AI agents to build, test, debug, and interact with Kotlin Multiplatform Mobile (Android/iOS) applications through automated build pipelines, UI automation, crash analysis, and app state inspection.
README
<p align="center"> <img src="logo.png" alt="Specter MCP Logo" width="400"> </p>
<h1 align="center">Specter MCP</h1>
<p align="center"> <strong>KMM Diagnostic & Execution Engine</strong><br> An MCP server providing "hands and eyes" for AI agents working with Kotlin Multiplatform Mobile projects. </p>
<p align="center"> <a href="https://www.npmjs.com/package/specter-mcp"><img src="https://img.shields.io/npm/v/specter-mcp.svg" alt="npm version"></a> <a href="https://www.npmjs.com/package/specter-mcp"><img src="https://img.shields.io/npm/dm/specter-mcp.svg" alt="npm downloads"></a> <a href="https://github.com/abd3lraouf/specter-mcp/blob/main/LICENSE"><img src="https://img.shields.io/npm/l/specter-mcp.svg" alt="license"></a> <a href="https://nodejs.org/"><img src="https://img.shields.io/node/v/specter-mcp.svg" alt="node version"></a> </p>
What is Specter MCP?
Specter MCP enables AI agents (Claude, GPT, etc.) to build, test, debug, and interact with Android and iOS applications through the Model Context Protocol. Think of it as giving your AI assistant the ability to:
- Build and deploy your mobile apps
- Take screenshots and interact with UI elements
- Run unit tests and E2E tests (Maestro)
- Analyze crash logs and debug issues
- Inspect app state (preferences, databases, logs)
Prerequisites
| Requirement | Version | Verify Command |
|---|---|---|
| Node.js | 20+ | node --version |
| Android SDK | Any | adb --version |
| Xcode CLI (macOS) | Any | xcrun --version |
| Maestro (optional) | Any | maestro --version |
Quick Setup
# Android SDK (if not installed via Android Studio)
export ANDROID_SDK_ROOT="$HOME/Library/Android/sdk"
export PATH="$PATH:$ANDROID_SDK_ROOT/platform-tools"
# iOS (macOS only)
xcode-select --install
sudo xcodebuild -license accept
# Maestro (optional, for E2E testing)
curl -Ls "https://get.maestro.mobile.dev" | bash
Installation
Option 1: npm (Recommended)
npm install -g specter-mcp
Option 2: From Source
git clone https://github.com/abd3lraouf/specter-mcp.git
cd specter-mcp
npm install && npm run build
Configuration
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"specter-mcp": {
"command": "specter-mcp"
}
}
}
Claude Code
Add to your project's .mcp.json:
{
"mcpServers": {
"specter-mcp": {
"command": "specter-mcp"
}
}
}
With Environment Variables
{
"mcpServers": {
"specter-mcp": {
"command": "specter-mcp",
"env": {
"SPECTER_DEBUG": "true",
"ANDROID_SDK_ROOT": "/path/to/android/sdk"
}
}
}
}
From Source
{
"mcpServers": {
"specter-mcp": {
"command": "node",
"args": ["/absolute/path/to/specter-mcp/dist/index.js"]
}
}
}
Available Tools (15)
| Category | Tool | Description |
|---|---|---|
| Build | build_app |
Build Android/iOS app (debug/release) |
install_app |
Install APK or .app on device | |
launch_app |
Launch installed app | |
| UI | get_ui_context |
Screenshot + UI hierarchy |
interact_with_ui |
Tap, swipe, input text | |
| Testing | run_unit_tests |
Run unit tests |
run_maestro_flow |
Run Maestro E2E flows | |
run_linter |
Detekt, SwiftLint, ktlint | |
| Environment | list_devices |
List emulators/simulators |
manage_env |
Boot/shutdown devices | |
clean_project |
Clean build caches | |
| Debug | analyze_crash |
Parse crash logs, symbolicate |
inspect_logs |
Filter device logs | |
inspect_app_state |
Read prefs, databases | |
| Navigation | deep_link_navigate |
Open deep links |
Usage Examples
Build & Deploy
You: Build my Android app in debug mode and install it
Claude: I'll build and deploy your app.
→ build_app(platform: "android", variant: "debug")
→ install_app(platform: "android", appPath: "...")
→ launch_app(platform: "android", appId: "com.example.app")
Debug a Crash
You: My iOS app crashed, help me debug it
Claude: Let me analyze the crash.
→ analyze_crash(platform: "ios", appId: "com.example.app")
→ inspect_logs(platform: "ios", minLevel: "error")
UI Testing
You: Take a screenshot and tap the login button
Claude: I'll capture the UI and interact with it.
→ get_ui_context(platform: "android")
→ interact_with_ui(platform: "android", action: "tap", element: "Login")
Run E2E Tests
You: Run my login flow test on both platforms
Claude: Running Maestro flows.
→ run_maestro_flow(platform: "android", flowPath: "./maestro/login.yaml")
→ run_maestro_flow(platform: "ios", flowPath: "./maestro/login.yaml")
Environment Variables
| Variable | Default | Description |
|---|---|---|
SPECTER_DEBUG |
false |
Enable debug logging |
SPECTER_LOG_LEVEL |
info |
Log level (error/warn/info/debug) |
SPECTER_TIMEOUT |
60000 |
Default timeout (ms) |
ANDROID_SDK_ROOT |
auto | Android SDK path |
SPECTER_ANDROID_DEVICE |
- | Default Android device |
SPECTER_IOS_DEVICE |
booted |
Default iOS simulator |
Troubleshooting
"adb: command not found"
export PATH="$PATH:$ANDROID_SDK_ROOT/platform-tools"
"No devices found"
# Android: Start emulator
emulator -avd Pixel_6_API_34
# iOS: Boot simulator
xcrun simctl boot "iPhone 15 Pro"
"xcrun: error: unable to find utility"
xcode-select --install
Debug Mode
{
"env": {
"SPECTER_DEBUG": "true",
"SPECTER_LOG_LEVEL": "debug"
}
}
Project Structure
src/
├── index.ts # MCP server entry
├── config.ts # Configuration
├── platforms/ # Android/iOS utilities
│ ├── android/ # ADB, Gradle, logcat
│ └── ios/ # simctl, xcodebuild, crash parsing
├── tools/ # MCP tool implementations
│ ├── build/ # build_app, install_app, launch_app
│ ├── ui/ # get_ui_context, interact_with_ui
│ ├── testing/ # run_unit_tests, run_maestro_flow, run_linter
│ ├── environment/ # list_devices, manage_env, clean_project
│ ├── crash/ # analyze_crash
│ ├── navigation/ # deep_link_navigate
│ └── observability/ # inspect_logs, inspect_app_state
└── utils/ # Shell, image processing, XML parsing
Development
npm install # Install dependencies
npm run build # Build TypeScript
npm test # Run tests (695 tests)
npm run test:coverage # Coverage report
npm run lint # ESLint
npm run typecheck # Type check
Documentation
- API Reference — All 15 tools with parameters
- Configuration Guide — Environment variables & setup
- Getting Started — First steps
License
MIT © Specter MCP Contributors
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.