MCPXcode

by everettjf

8 188 downloads Not rated yet MIT

GitHub

Other

About

MCPXcode is an open-source implementation of the Model Context Protocol (MCP) for Xcode. It bridges Xcode’s development environment with AI assistants by wrapping command-line tools like xcrun and xctrace and leveraging macOS accessibility features, enabling structured context…

Details

License: MIT

Explore

- ⬜ MCP-compliant Python client library
- ⬜ Context-aware integration with AI-powered CI/CD tools
- ⬜ Semantic context monitoring dashboard

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name MCPXcode

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

From the repository

Install uv, clone the repository, add the mcp[cli] dependency, then configure your MCP client (e.g., Claude Desktop) with the JSON snippet specifying the uv command, directory path, and main.py as the run target. Once configured, the server exposes MCP tools that can be invoked via natural language prompts.

`list_devices`

List all available simulator devices with detailed information

`boot_device`

Boot a specific simulator device identified by its UDID

`shutdown_device`

Shutdown a running simulator device

`install_app`

Install an application on a simulator device

`launch_app`

Launch an installed application on a simulator device

`get_sdk_path`

Get the path of the current SDK

`get_sdk_version`

Get the version of the current SDK

`get_sdk_platform_path`

Get the platform path of the current SDK

`find_developer_tool`

Find the path of a specific developer tool

`run_tool_with_sdk`

Run a developer tool with a specific SDK

`xcrun_list_sdks`

List all available SDKs with detailed information

`xcrun_list_schemes`

List all schemes in a specified Xcode project

`xcrun_build`

Build an Xcode project with specified scheme and configuration

`xcrun_validate_app`

Validate an app before submission to App Store

`xcrun_upload_app`

Upload an app to App Store Connect

`xcrun_swift_symbols`

Extract Swift symbols from a binary file

`xcrun_otool_headers`

Show Mach-O headers of a binary file

`xcrun_otool_libraries`

Show linked libraries of a binary file

`xcrun_nm_symbols`

Show symbols in a binary file

`xctrace_devices`

List available devices for tracing

`xctrace_templates`

List available templates for tracing

`xctrace_record`

Record app performance using a specified template

`xctrace_record_advanced`

Record app performance with advanced options

`xctrace_attach_process`

Attach to a running process for tracing

`xctrace_export`

Export trace data to a specified format

`xctrace_diagnose`

Diagnose a trace archive for issues

`xctrace_document`

Generate documentation for a template

`xctrace_analyze`

Analyze a trace file and generate performance reports

`xctrace_compare`

Compare two trace files and generate a comparison report

- xcrun Tool Extensions
- Context-aware interfaces for common xcrun commands
- Structured output formatting for AI consumption
- Semantic error handling and diagnostic reporting

- xctrace Tool Extensions
- Context-enhanced profiling and tracing for iOS/macOS applications
- Structured performance metrics collection for AI analysis
- Trace data processing with semantic context

| Tool | Description | Example Prompt |
|------|-------------|----------------|
| list_devices | List all available simulator devices with detailed information | "Show me all available iOS simulator devices and their status." |
| boot_device | Boot a specific simulator device identified by its UDID | "Boot the iPhone 14 Pro simulator with UDID A1B2C3D4-E5F6-7890-1234-567890ABCDEF." |
| shutdown_device | Shutdown a running simulator device | "Shutdown the currently running iPhone simulator with UDID A1B2C3D4-E5F6-7890-1234-567890ABCDEF." |
| install_app | Install an application on a simulator device | "Install the app at path /Users/username/MyApp.app on the iPhone 14 simulator." |
| launch_app | Launch an installed application on a simulator device | "Launch the app with bundle ID com.example.myapp on the iPhone 14 simulator." |

| Tool | Description | Example Prompt |
|------|-------------|----------------|
| get_sdk_path | Get the path of the current SDK | "What is the path to the current iOS SDK?" |
| get_sdk_version | Get the version of the current SDK | "What version of the iOS SDK am I using?" |
| get_sdk_platform_path | Get the platform path of the current SDK | "Where are the iOS platform files located?" |
| find_developer_tool | Find the path of a specific developer tool | "Where is the 'lldb' binary located in the Xcode toolchain?" |
| run_tool_with_sdk | Run a developer tool with a specific SDK | "Run the 'clang' tool with the iOS SDK to compile my source file." |

| Tool | Description | Example Prompt |
|------|-------------|----------------|
| xcrun_list_sdks | List all available SDKs with detailed information | "Show me all available SDKs I can build against." |
| xcrun_list_schemes | List all schemes in a specified Xcode project | "What are all the build schemes in my MyApp.xcodeproj project?" |
| xcrun_build | Build an Xcode project with specified scheme and configuration | "Build my MyApp.xcodeproj project using the Debug configuration for the iPhone simulator." |
| xcrun_validate_app | Validate an app before submission to App Store | "Validate my MyApp.ipa file before submitting it to the App Store." |
| xcrun_upload_app | Upload an app to App Store Connect | "Upload my validated MyApp.ipa file to App Store Connect for review." |
| xcrun_swift_symbols | Extract Swift symbols from a binary file | "Extract and show me all Swift symbols from my app's binary." |
| xcrun_otool_headers | Show Mach-O headers of a binary file | "Show me the Mach-O headers of my app's binary file." |
| xcrun_otool_libraries | Show linked libraries of a binary file | "What libraries is my app's binary linked against?" |
| xcrun_nm_symbols | Show symbols in a binary file | "Show me all symbols in my app's binary file." |

| Tool | Description | Example Prompt |
|------|-------------|----------------|
| xctrace_devices | List available devices for tracing | "Show me all devices I can run performance traces on." |
| xctrace_templates | List available templates for tracing | "What trace templates are available for performance profiling?" |
| xctrace_record | Record app performance using a specified template | "Record a performance trace of my app using the Time Profiler template." |
| xctrace_record_advanced | Record app performance with advanced options | "Record a performance trace with custom template options and set the environment variable DEBUG=1." |
| xctrace_attach_process | Attach to a running process for tracing | "Attach a performance tracer to my running app with process ID 12345." |
| xctrace_export | Export trace data to a specified format | "Export my trace.trace file to JSON format for analysis." |
| xctrace_diagnose | Diagnose a trace archive for issues | "Analyze my trace file for any performance issues or problems." |
| xctrace_document | Generate documentation for a template | "Create documentation for the Allocations template so I can understand its metrics." |
| xctrace_analyze | Analyze a trace file and generate performance reports | "Generate performance reports from my time profiler trace file." |
| xctrace_compare | Compare two trace files and generate a comparison report | "Compare the performance between trace files from version 1.0 and version 2.0 of my app." |

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcpxcode": {
            "MCPXcode": {
                "command": "uv",
                "args": [
                    "--directory",
                    "<Path>/MCPXcode",
                    "run",
                    "main.py"
                ]
            }
        }
    }
}

McpServers

{
    "MCPXcode": {
        "command": "uv",
        "args": [
            "--directory",
            "<Path>/MCPXcode",
            "run",
            "main.py"
        ]
    }
}

!!! This Project is in Active Development, So May Have Unexpected Issues

Introduction

MCPXcode is an open-source implementation of the Model Context Protocol (MCP) for Xcode. It enables seamless integration between Xcode and AI assistants by providing a structured protocol for context exchange and tool execution within the Xcode environment.

Following the MCP specification, this project creates a bridge between Xcode's development environment and AI tools, allowing for enhanced developer workflows through contextual understanding and programmable interactions. It wraps common command-line tools (xcrun, xctrace) and leverages macOS accessibility features to enable AI-assisted automation of Xcode operations.

Screenshots

Installation

```bash

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Explore

Setting up with Highlight

From the repository

list_devices

boot_device

shutdown_device

install_app

launch_app

get_sdk_path

get_sdk_version

get_sdk_platform_path

find_developer_tool

run_tool_with_sdk

xcrun_list_sdks

xcrun_list_schemes

xcrun_build

xcrun_validate_app

xcrun_upload_app

xcrun_swift_symbols

xcrun_otool_headers

xcrun_otool_libraries

xcrun_nm_symbols

xctrace_devices

xctrace_templates

xctrace_record

xctrace_record_advanced

xctrace_attach_process

xctrace_export

xctrace_diagnose

xctrace_document

xctrace_analyze

xctrace_compare

Claude Desktop / Cursor

McpServers

Introduction

Screenshots

Installation

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

`list_devices`

`boot_device`

`shutdown_device`

`install_app`

`launch_app`

`get_sdk_path`

`get_sdk_version`

`get_sdk_platform_path`

`find_developer_tool`

`run_tool_with_sdk`

`xcrun_list_sdks`

`xcrun_list_schemes`

`xcrun_build`

`xcrun_validate_app`

`xcrun_upload_app`

`xcrun_swift_symbols`

`xcrun_otool_headers`

`xcrun_otool_libraries`

`xcrun_nm_symbols`

`xctrace_devices`

`xctrace_templates`

`xctrace_record`

`xctrace_record_advanced`

`xctrace_attach_process`

`xctrace_export`

`xctrace_diagnose`

`xctrace_document`

`xctrace_analyze`

`xctrace_compare`