Xcodebuildmcp

xcodebuildmcp is a Model Context Protocol server that exposes Xcode build, test, and device management tools for AI coding agents to automate iOS and macOS development workflows. It operates as a background daemon per workspace, communicating tool requests and responses over standard input/output using JSON-RPC messages, and streams progress and results as newline-delimited JSON objects for machine parsing.

The project provides an interactive setup wizard and file-based client configuration to install skill files into predefined directories for supported AI coding clients. It manages the full lifecycle of iOS simulators programmatically — booting, installing apps, launching with arguments, capturing logs, and recording video — and wraps Apple's xcodebuild tool as a child process to stream its output in real time. The tool also handles physical device deployment, building, signing, installing, and launching apps on real hardware over USB or Wi-Fi for unattended testing.

Beyond build and test automation, xcodebuildmcp includes capabilities for project discovery, Swift package management, code coverage reporting, and UI interaction automation through tap, swipe, type, and gesture commands. It supports LLDB debugging by attaching a debugger to running processes, setting breakpoints, inspecting stack frames, and executing raw LLDB commands. The project integrates with a wide range of AI coding clients and editors including Claude Code, Cursor, VS Code, Windsurf, and others through automated skill installation and MCP client configuration.

Features

MCP Servers - Launches a Model Context Protocol server on stdio for integration with MCP-compatible AI coding agents.
Model Context Protocol Servers - Exposes Xcode build, test, and device management tools to AI coding agents via the Model Context Protocol.
MCP Server Integrations - Connects AI coding agents to Xcode projects via the Model Context Protocol for automated iOS and macOS development.
MCP-over-STDIO Transports - Communicates tool requests and responses over standard input/output using JSON-RPC messages for MCP integration.
MCP Server Configurations - Configures MCP servers across multiple AI coding clients with automated skill installation and client integration.
iOS Device Builds - Builds an iOS app and launches it on a physical device, accepting runtime arguments for configuration.
Newline-Delimited JSON Streams - Emits progress and results as newline-delimited JSON objects for machine parsing and shell piping.
AI Agent Priming Skills - Teach an AI agent the correct tool names, CLI equivalents, and workflow patterns so it stops guessing flag names.
iOS Simulator Builds - Builds an iOS app and launches it on a specified simulator, accepting optional launch arguments for testing.
Client Configurations - Configures any MCP-compatible editor or AI agent to connect to the server by pasting a JSON block with the command and arguments.
Per-Workspace Daemons - Auto-starts a stateful background process per workspace that persists between commands for long-running operations.
Xcode Build Automation - Compiles Xcode projects, runs XCTest suites with live progress, and generates code coverage reports from a CLI or agent interface.
iOS Device Installations - Builds, installs, launches, and tests apps on iOS or macOS hardware devices after signing is configured.
xcodebuild Wrappers - Invokes Apple's xcodebuild tool as a child process and streams its output in real time for build automation.
iOS Physical Device Runners - Runs an iOS app on a connected physical device with custom runtime arguments for unattended testing.
Physical Device Deployments - Installs and launches apps on paired iPhones, iPads, Apple Watches, and Vision Pros over USB or Wi-Fi.
iOS Simulator Lifecycle Controllers - Boots, installs, launches, captures logs, records video, and resets state on iOS simulators programmatically.
Background Daemons - Runs a persistent background daemon per workspace to maintain stateful debugging sessions across CLI invocations.
Multi-Target Build and Test - Compiles, tests, and cleans targets for simulators, physical devices, and macOS using structured tool calls.
Single-Call Build and Launch - Compiles, installs, launches, and streams logs for a target in a single tool call to eliminate multi-step workflows.
Test Suite Progress Streams - Executes XCTest suites on simulators and devices, streaming test results and progress in real time.
Xcode Test Runners - Provides an agent that executes XCTest suites with live progress streaming and generates code coverage reports.
Skill Installation - Detects installed AI coding clients and places the skill file into the correct directory for each one automatically.
Agent Skill-Only Installations - Installs MCP or CLI agent skill files into supported coding assistants like Claude Code or Cursor.
Xcode Skill Installations - Installs pre-configured skill files that prime AI agents with Xcode tool conventions and workflows.
MCP Server Registrations - Adds the MCP server to Claude Code via a single CLI command so the agent can build and test Xcode projects.
Xcode Build Instructions - Installs skills that instruct AI agents on how to use MCP server tools or CLI for Xcode tasks.
Claude Desktop Configurations - Adds the MCP server to Claude Desktop's configuration file for in-app Xcode project control.
Xcode Project Scanners - Scans the filesystem to locate Xcode project, workspace, and Swift package manifest files automatically.
LLDB Agent Debugging Bridges - Attaches a debugger to running apps, sets breakpoints, inspects stack frames, and executes raw LLDB commands for interactive debugging.
macOS App Launchers - Builds a macOS app and launches it directly on the host machine, supporting runtime argument injection.
Real-Time Output Streaming - Streams progress and subprocess output live to stdout in text or JSONL format for immediate feedback.
Xcode Session Defaults - Stores workspace, scheme, and simulator settings so subsequent tool calls reuse them automatically.
Setup Wizards - Guides users through project configuration via a terminal-based questionnaire for initial setup.
Swift Package Management - Builds, tests, and runs Swift packages and executables with background process management through a daemon.
Xcode Code Signing Setups - Sets up code signing in Xcode so device build, install, and launch tools work unattended.
iOS App Launchers - Starts an already-installed app on a simulator or device by bundle ID, passing custom launch arguments.
Skill File Installers - Installs skill files into predefined directories for each supported AI coding client automatically.
Simulator Video Recorders - Captures video recordings of simulator activity for bug reports and automated UI flow documentation.
Apple Device Runtime Log Captures - Retrieves runtime logs and process IDs from an app running on a connected Apple device for debugging.
Code Coverage Reportings - Generates per-target summaries and function-level reports of uncovered lines from test result data.
UI Element Interactions - Automates tap, swipe, type, gesture, and inspection of semantic element references from the view hierarchy.
Development Tools - Scaffold, build, and test iOS and macOS apps

getsentry/XcodeBuildMCP

4,367View on GitHub

XcodeBuildMCP is a Model Context Protocol server and development tool bridge that provides AI agents with the ability to control xcodebuild, manage simulators, and automate the compilation and execution of Apple platform applications. It functions as a persistent daemon that proxies native IDE build and debug capabilities to external clients and agents. The project distinguishes itself by using the Model Context Protocol to expose build and device management tools through a standardized interface. It implements specialized skill priming and instruction configuration to ensure AI agents can in

CursorTouch/Windows-MCP

4,373View on GitHub

This is a Model Context Protocol server that exposes Windows desktop automation and system administration functions to large language models. It provides programmatic control of mouse, keyboard, windows, and UI elements on Windows through simulated user input, while also enabling LLMs to manage the Windows registry, processes, files, and execute PowerShell commands through a remote interface. The server supports multiple transport protocols including stdio, SSE, and streamable HTTP, allowing flexible integration with different language model clients. It implements OAuth 2.0 with PKCE for secu

MervinPraison/PraisonAI

5,592View on GitHub

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

tobi/qmd

9,498View on GitHub

qmd is a local semantic search engine and RAG knowledge base indexer that functions as a Model Context Protocol server. It converts local documents, markdown files, and codebases into a searchable database to provide retrieval augmented generation capabilities for AI agents. The system exposes its search and retrieval tools via stdio or HTTP. It utilizes local model files for embeddings and reranking, supporting query expansion across multiple languages. The project employs abstract syntax tree based chunking to split source code at function and class boundaries. It implements hybrid vector-

cameroncookexcodebuildmcp

Features