Model Context Protocol Server

DevTools MCP Server

A Python MCP server that gives AI agents real development tooling for mobile, web, and server workflows.

DevTools MCP Server connects AI agents to local development tools, so agent workflows can build projects, inspect simulator state, trigger Xcode, and run audits through a structured MCP interface.

The current implementation focuses on iOS, with tools for simulator builds, simulator discovery, Xcode run/stop automation, and pre-commit audits for changed files.

What this demonstrates: Practical agent tooling around real developer workflows, including host-machine automation, structured build errors, multi-project configuration, and remote SSE access for container-to-host setups.

MCP
Python
Server
Tool registry for agents
iOS
Build
Automation
Simulator build workflow
Xcode
Run
Control
AppleScript commands
SSE
Remote
Access
Container-to-host use

Technical Highlights

Build

Structured iOS Builds

Runs simulator builds and parses build failures into file, line, column, and message fields that agents can act on directly.

Sim

Simulator Discovery

Lists available simulators with UDID, state, and OS version so agents can select a usable target instead of guessing.

Xcode

Xcode Run And Stop

Triggers Xcode run and stop actions through AppleScript, allowing local app execution to stay connected to agent workflows.

Audit

Changed File Audits

Checks changed files for design-system compliance, Swift hygiene issues, and metadata concerns before commits.

Technology Stack

MCP Server

Python Model Context Protocol SSE transport pytest

Developer Tooling

xcodebuild Xcode AppleScript iOS Simulator

Repository Entry Points

The repository is organized around an MCP server entry point, platform drivers, audit checks, and setup documentation for local and remote agent use.

Review the MCP implementation, iOS tooling surface, and setup path for connecting AI agents to local development workflows.