What are the system requirements?
macOS is required, along with Xcode and Python 3.10+. The `uv` package manager is also needed for installation.
@drewster99
Basic information
MCP Server for interacting with Xcode
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"xcode-mcp-server": {
"command": "uvx",
"args": [
"xcode-mcp-server"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Xcode MCP Server is an MCP (Model Context Protocol) server that enables AI assistants to control and interact with Xcode for Apple platform development. It is built for macOS and requires Xcode and Python 3.10+.
Install via uv and configure in your MCP client (Claude Code, Claude Desktop, or Cursor) using the provided JSON commands. Security is managed via the XCODEMCP_ALLOWED_FOLDERS environment variable to restrict which directories the server can access.
macOS is required, along with Xcode and Python 3.10+. The `uv` package manager is also needed for installation.
Set the `XCODEMCP_ALLOWED_FOLDERS` environment variable to a colon-separated list of absolute directory paths. If unset, the server defaults to your home directory.
It allows AI assistants to discover projects, build and run apps, execute tests, debug build failures, capture console output and screenshots, and manage simulators.
Add an entry to `~/Library/Application Support/Claude/claude_desktop_config.json` with the command `uvx` and argument `xcode-mcp-server`. You can optionally add an `env` section for folder restrictions.
AppleScript syntax may need adjustments for specific Xcode versions, and some operations require the project to be open in Xcode first.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
🚀 The fast, Pythonic way to build MCP servers and clients.
A curated list of references for MLOps
Hindsight: Agent Memory That Learns

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Comments