xcode-bridge

A guide for using the Xcode MCP bridge, which connects coding tools with Xcode, Apple's development environment. It includes support for rendering SwiftUI previews, which show an app interface while it is being built.

In plain words
What is it for?
Use it when working with SwiftUI previews or when you need coding tools to interact directly with Xcode.
Why use it?
It explains the requirements and permission step needed before interacting with Xcode through the bridge.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/vivqu/swiftuiagenttoolkit/xcode-bridge
Any agent
npx skills add vivqu/SwiftUIAgentToolkit --skill xcode-bridge
Clone the repo
git clone --depth 1 https://github.com/vivqu/SwiftUIAgentToolkit

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,061 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.01061
Opus 5 $0.00015 $0.00531
Sonnet 5 $0.00006 $0.00212
Haiku 4.5 $0.00003 $0.00106

Measured 2d ago against content hash d12efc016c3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xcode-bridge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/xcode-bridge/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Xcode MCP Bridge

Use the Xcode MCP bridge (mcp__xcode__* tools) when you need to render SwiftUI Previews or interact with Xcode's IDE directly.

Prerequisites

Before calling any xcode bridge tool, verify:

  1. Xcode is open and running
  2. The xcode MCP server is connected — if tools are unavailable, tell the user to open Xcode and restart Claude Code

Permission Prompt — Required Before Every Session

Xcode will show an "Allow 'claude-code' to access Xcode?" dialog on the first tool call of every Claude Code session. This is a macOS TCC (privacy) restriction: because Claude Code CLI has no persistent bundle identifier, the grant cannot be saved and must be re-approved each session.

Before making any xcode bridge tool call, use AskUserQuestion to warn the user:

AskUserQuestion:
  question: "Xcode will show an 'Allow claude-code to access Xcode?' dialog on the next step.
             Please click Allow when it appears, then confirm here."
  options:
    - "I'm watching Xcode and will click Allow"
    - "I already clicked Allow this session"

Only proceed with tool calls after the user confirms. If a tool call hangs or returns an error after this, ask the user to check Xcode for a pending Allow dialog.

Tip for reducing prompts: Set up mcp-proxy as a long-lived bridge process. This lets macOS grant permission once to the proxy rather than re-prompting on every session. See the Swift Forums thread for setup instructions.

Standard Workflow

Every xcode bridge tool requires a tabIdentifier. Always start by calling XcodeListWindows:

1. XcodeListWindows
   → returns tabIdentifier (e.g. "windowtab1") and workspacePath (e.g. ".../MyApp/MyApp.xcodeproj")

2. Derive sourceFilePath (project-relative, NOT absolute)
   → strip everything up to and including the .xcodeproj parent directory
   → e.g. workspacePath = "/Users/me/code/MyApp/MyApp.xcodeproj"
        file at        = "/Users/me/code/MyApp/MyApp/ContentView.swift"
        sourceFilePath = "MyApp/ContentView.swift"

3. Call the tool with tabIdentifier + sourceFilePath

Read the full file on GitHub · 95 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 95 lines · 31 tokens per session scan A d12efc016c3d

Subscribe to this mod's changes

xcode-bridge is a skill published in the GitHub repository vivqu/SwiftUIAgentToolkit (11 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 1,061 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens