Xcode MCP Server
A Model Context Protocol server that enables AI assistants to build and test Xcode projects directly through a standardized interface, with capabilities for running tests, monitoring progress, and accessing logs in real-time.
PolarVista
README
Xcode MCP Server
<p align="center"> <strong>A Model Context Protocol server for building Xcode projects directly from LLM applications</strong> </p>
The Xcode MCP Server provides a Model Context Protocol interface for building and testing Xcode projects. It enables AI assistants to directly trigger builds, run tests, monitor progress, and access logs through a standardized interface.
Features
- Build Xcode projects with custom schemes and configurations
- Run unit tests with granular control (run specific tests or skip tests)
- Generate code coverage reports
- Stream build and test logs in real-time
- Access detailed build and test reports
- JSON-formatted output
- Automatic log persistence
Requirements
- Node.js 16+
- Xcode Command Line Tools
- TypeScript
- MCP-compatible client (e.g., Claude Desktop)
Installation
# Clone the repository
git clone https://github.com/PolarVista/Xcode-mcp-server.git
cd xcode-mcp-server
# Install dependencies
npm install
# Build the server
npm run build
Usage with Claude Desktop
-
Start the server:
npm run start /path/to/build/logs/directory
-
In Claude Desktop settings:
"command": "node", "args": ["/path/to/the/xcode-mcp-server/build/index.js", "/path/to/your/project/folder"], "env": { "PATH": "/usr/bin:/bin:/usr/local/bin:/usr/sbin:/sbin" }
Available Tools
build_project
Builds an Xcode project with specified parameters.
Parameters:
projectPath
(required): Path to the .xcodeproj or .xcworkspacescheme
(required): Build scheme nameconfiguration
(optional): Build configuration (Debug/Release, defaults to Debug)destination
(optional): Build destination (defaults to "platform=iOS Simulator,name=iPhone 15 Pro")
Example usage in Claude:
build_project({
projectPath: "/path/to/Project.xcodeproj",
scheme: "MyApp",
configuration: "Debug"
})
run_tests
Runs unit tests with optional filtering.
Parameters:
projectPath
(required): Path to the .xcodeproj or .xcworkspacescheme
(required): Test scheme nametestIdentifier
(optional): Specific test to run (e.g., 'MyTests/testExample')skipTests
(optional): Array of test identifiers to skipconfiguration
(optional): Build configuration (Debug/Release, defaults to Debug)destination
(optional): Test destination (defaults to "platform=iOS Simulator,name=iPhone 15 Pro")
Example usage in Claude:
run_tests({
projectPath: "/path/to/Project.xcodeproj",
scheme: "MyAppTests",
testIdentifier: "LoginTests/testSuccessfulLogin",
skipTests: ["PerformanceTests/testLargeDataLoad"],
configuration: "Debug"
})
Logs
- All logs are stored in the specified base directory under
build-logs/
- Build operations create:
- Plain text log (
build-[timestamp].log
) - JSON-formatted log (
build-[timestamp].log.json
) - Xcode report (
report-[timestamp].txt
)
- Plain text log (
- Test operations create:
- Test log (
test-[timestamp].log
) - JSON-formatted log (
test-[timestamp].log.json
) - Test report (
test-report-[timestamp].txt
) - Code coverage report (
coverage-[timestamp].txt
)
- Test log (
- Latest log (build or test) is accessible via the
xcode-build://latest-log
resource
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.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
AIO-MCP Server
🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from
Persistent Knowledge Graph
An implementation of persistent memory for Claude using a local knowledge graph, allowing the AI to remember information about users across conversations with customizable storage location.
Hyperbrowser MCP Server
Welcome to Hyperbrowser, the Internet for AI. Hyperbrowser is the next-generation platform empowering AI agents and enabling effortless, scalable browser automation. Built specifically for AI developers, it eliminates the headaches of local infrastructure and performance bottlenecks, allowing you to
React MCP
react-mcp integrates with Claude Desktop, enabling the creation and modification of React apps based on user prompts