ios-agent
This server provides iOS/Swift project analysis, review, planning, reference lookup, and simulator/build tooling.
Analyze Swift projects and run focused reviews for concurrency, architecture, SwiftUI, availability, App Store readiness, memory, security, testing, performance, and App Intents.
Lint Agent Skill repositories for metadata, subagents, mirrored docs, and broken paths.
Search Apple technologies, updates, and bundled local Swift/guide references.
Plan an iOS app from a brief and plan layered app-icon artwork.
Create editable Swift app starters with optional XcodeGen/icon layers.
Manage simulators: list, boot, shutdown, show/preview, install, launch, terminate, open deep links, and screenshot.
Build Xcode projects/workspaces, run tests, and inspect Xcode/simulator environments.
Prepare a local, privacy-preserving issue report for ios-agent-mcp failures.
Provides access to local Apple developer references and an Apple technology catalog to support app development.
Enables building, reviewing, and testing iOS apps, including app scaffolding, simulator workflows, and offline source-library searches.
Supports creating and reviewing Swift apps with tools for compiling, testing, and searching Swift source and guidance.
Integrates with Xcode to build, test, launch, and capture simulator screenshots for iOS apps.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ios-agent Build and test my iOS app in the Xcode simulator"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
iOS Agent Skill
Give your coding agent the Apple references, Swift source and local tools it needs to build and review an iOS app.

Watch the website walkthrough · Explore the website
Describe an app in one sentence and the /ios-build agent plans it, writes the SwiftUI code and Xcode project, then builds and runs it in the simulator (what has been verified, example apps on the website). For an existing project, the same package gives your coding agent reviews, local Apple references and simulator tools to check its work.
Explore the website · Client setup guides · npm · Release notes
Build an app from one sentence
/ios-build "<what you want>" asks Claude Code to plan an iOS app, write its SwiftUI code and Xcode project, apply capability modules (sign-in, storage, payments, maps and more), then build, run and screenshot it in the iOS Simulator, ending with a report of what needs your accounts or money. Published tools are in ios-agent-mcp 2.10.2 (npm verified October 15, 2026), including plan-driven design tokens, sample data, palette-aligned assets, light/dark/XXL screenshot evidence, deployment-target checks and App Store readiness reports. Four existing apps built and ran on Xcode 27.0; see examples/agent for refreshed evidence.
Quickstart
Install the published server and Claude Code command:
claude mcp add ios-agent -- npx -y ios-agent-mcp@latest
npx -y ios-agent-mcp@latest install-command --globalThen, in any Claude Code session on a Mac with Xcode 16 or later:
/ios-build "A habit tracker with a list, a detail screen, and settings with dark mode toggle"Shipping (unreleased GitHub source): ios-agent-mcp ship prepares screenshot sets and metadata, then offers separately approved signing/archive and TestFlight upload steps. Setup and limitations. Live signed distribution is not yet verified; npm is unchanged.
Windows/Linux or cloud client: the GitHub source now includes build --remote for unsigned builds and simulator screenshots on GitHub Actions. It requires a destination repository, GitHub CLI authentication and pinned toolkit/Xcode versions. See remote macOS setup and billing. npm publication is deferred.
XcodeGen is optional: without it, the agent writes a folder-synchronized Xcode project itself. The steps are described in docs/tooling/ios-build-agent.md. The four screenshot examples reused existing app folders; this exact Claude Code quickstart has not yet been run from planning through code generation in one Mac session. A separate fresh Studio/Codex notes-app run completed planning, generation, builds, simulator captures and tests on a Mac.
Examples
Habit tracker | Notes with search | Three-tab feed | Food delivery |
Plans, generated sources, run reports and what was and was not exercised: examples/agent.
Capabilities
Every capability is a folder in capabilities/ with a manifest, recipe, Swift template, apply hook and verify hook. The catalog lists the wider landscape for planning and cost estimates. The counts below are generated from the manifests.
Status | Capabilities |
Verified on a Mac | 7 |
Module exists, not yet verified on a Mac | 41 |
...of which the Swift compiled on a Mac (combined compile check) | 41 |
Blocked | 0 |
Listed for planning only | 114 |
162 catalog entries in 31 categories; generated from capabilities/CATALOG.md.
Needs your accounts
Simulator builds can use placeholder configuration for supported services. Capabilities that need a service declare the keys in their manifest; a successful build does not verify those services or their runtime transactions. Client keys, such as a publishable key, go in the project's gitignored .env file and reach the app through a generated xcconfig. Until they are set, the keys are REPLACE_ME placeholders and the app can show a configuration message. Server secrets are never put in the app. PLAN.md lists what each run needs and the cost model of each service. Device signing, TestFlight and publication have separate Apple account and provisioning requirements.
Not yet
The design-system, firebase-auth, firebase-firestore, google-sign-in, stripe-payments, rive-animation and webview-animation capabilities have passed isolated Mac compile verification. Provider accounts and runtime transactions remain unverified; a combined compile check is not a substitute for each module's verify run (see the compile check).
The agent's build, simulator launch and per-screen capture stages ran on Mac for these four existing examples. Their planning and code-generation sessions were separate. A subsequent fresh Studio/Codex notes-app run completed the shared loop with 11 passing native tests; the Claude Code quickstart still needs its own end-to-end run.
Taps and scrolling during the agent's own screenshots, and device builds, are not done. A separate Habit Tracker simulator test verified one navigation and completion-state interaction; it issued a swipe without asserting the scroll position. In the food-delivery example the StoreKit purchase and the Live Activity were not exercised.
Related MCP server: Apple RAG MCP
Which workflow to use
You want to | Use | Notes |
Build a new app from a description |
| Plans, writes, builds, runs and screenshots; see above. Available in npm 2.10.2 and GitHub main. |
Make an existing project pass your own acceptance tests |
| Runs the checks you write and asks Claude to repair failures; see the app-building loop and the Reading List demo. |
Get an editable starter only |
| A starting point with a brief, not a finished app. |
Review or extend code you already have | The MCP tools below | File-located reviews, local references, assets and simulator checks. |
Start with one connection
For Claude Code:
claude mcp add ios-agent -- npx -y ios-agent-mcp@latestSet up ChatGPT/Codex, Gemini CLI or Muse. One npm package includes reviews, local references, app scaffolding and simulator tools. Node.js 20+ is required; local iOS builds need macOS and Xcode; the GitHub-source remote lane runs those steps on Actions.
Then ask:
Build a SwiftUI reading list with local persistence, search and accessible empty/error states. Reuse the local source library. Build it, run the tests and capture simulator evidence. Explain any checks that fail.
For an existing app, provide its absolute project path and ask for a focused review before making changes.
What it helps you do
Feature | What you get |
Build an app from a sentence | The ios-build agent plans screens, data and capabilities, writes SwiftUI and the Xcode project, then builds, runs and screenshots the app in the simulator. Available in ios-agent-mcp 2.10.0. |
Start an app | An editable Swift starter, implementation brief and optional XcodeGen specification. |
Reuse Apple knowledge | Search local Swift source and guides in bounded sections, plus a dated directory of Apple technologies and release notes. |
Review Swift code | File-located findings for concurrency, architecture, SwiftUI, availability, security, performance and App Intents. |
Generate design assets | Named light/dark/high-contrast colors and an opaque 1024px app icon rendered locally from editable SVG layers. |
Review app color systems | Generate semantic palettes and inspect light, dark and high-contrast color evidence. |
Review backend integration | Identify supported services and review credential, auth, policy and networking evidence locally. |
Verify on a simulator | Build, test, install, launch and capture screenshots through Xcode. |
Review launch screens | Conservative target-aware checks for launch configuration, storyboards and asset references. |
Prepare a local release draft | Inspect selected-target facts, unresolved questions and hashed, resumable local packages without connecting to Apple. |
App Store Screenshot Studio (GitHub source) | Turn captures into localized screenshot sets with reusable layouts, neutral frames, a preview gallery and validated PNG exports. |
Apple system integrations (GitHub source) | Preview and review Calendar, Reminders, Contacts, Photos, Camera, Maps, Files, Sharing, Shortcuts and Notifications with permission and capability evidence. |
Asset generation · Review tools · Simulator setup · Apple release status
iOS UI pack (GitHub source): Find Apple's official Figma and Sketch kits, design guidance and a separate native SwiftUI component gallery in the iOS UI pack. Apple's design files are linked rather than redistributed; the gallery is original repository code, not an Apple product.
Create a starter directly:
npx -y ios-agent-mcp@latest new MyApp --brief "A reading list with local storage" --xcodegenThe starter is not a finished app: --xcodegen writes a project.yml that XcodeGen turns into a project. For a complete app from a description, use /ios-build. Generated app ownership and branding belong to the user.
See the evidence
The Reading List demo has persistence, search, simulator acceptance tests and captured screens. The four apps the /ios-build agent planned and wrote, with their plans, run reports and simulator screenshots, are in examples/agent.
The published npm 2.10.2 package includes the build-agent tools, deployment-target checks and App Store readiness reports. They include seven Apple system integration tools and nine Screenshot Studio tools. Static reviews are heuristics, not compiler diagnostics. The Apple directory is a reference map, not Apple's proprietary framework source or proof of 405 working integrations. Token savings have not been benchmarked. Build-loop verification limits.
Why use this alongside Xcode?
Xcode already ships agent expertise and build/test tools. Use those when they meet your needs. This repository adds shared guidance across these four client families, inspectable review rules, local source retrieval and repeatable asset workflows. It has not been established that it makes an AI outperform Xcode's skills or use fewer tokens.
Where the guidance comes from, evidence and unfinished work. The paired benchmark harness contains 20 Swift microtasks; results are not published, and it does not yet measure complete app builds.
Help improve the tools
Failure feedback belongs in your coding session: the observed error, the proposed fix and actual verification results. The source server adds troubleshooting guidance to returned tool errors; agent instructions also cover compiler/test failures. These messages do not appear in the app you are building.
prepare_issue_report lets your AI prepare a local report when an iOS Agent tool fails. It accepts fixed categories only, shows a preview and a duplicate-search link, and leaves public submission to you. No app source or logs are collected. Reporting workflow.
Included as an experimental tool in 2.7.1: optional private_feedback keeps approval in the AI chat and sends fixed categories to a private inbox through a configured HTTPS receiver. Hosting is not configured, so private submission is not live. It never silently submits or falls back to public issues.
Four client families, one project
Client | Setup and evidence |
Claude | Local MCP and source skill; your Claude client supplies the coding agent. |
ChatGPT / Codex | Codex local MCP; ChatGPT skills package or a separately configured HTTPS/private-tunnel MCP connection. Availability depends on account/workspace policy. |
Gemini CLI | Extension configuration and local MCP connection verified. |
Grok Build | Local MCP setup using the existing server. Grok web/API connections are separate. |
Muse Code | Skill discovery, MCP discovery (the 36-tool 2.7.0 server) and a Stop hook verified; model sessions and observer behavior remain unverified. |
Optional companion: an AI/ML API connector can run beside the local server for icon and asset concepts on the user's own account. It is not bundled, called or verified by this project.
The project focuses on these five families. For another client, open a client-support request or add a 👍 to an existing request. Votes inform priorities alongside feasibility and testing; they do not guarantee delivery. Existing experimental adapters are not actively maintained.
install.sh is optional: it installs source guidance for a chosen local client, not the MCP server or a browser plugin. Run bash install.sh --help after cloning. Most users should use the client setup guide above.
Apple catalog tracked: 99 technologies. Covered: 99. Planned: 0. Skipped: 0. Deprecated: 0. Coverage: 100.0%.
Source of truth: frameworks.json. Human index: docs/apple-framework-index.md.
Coverage counts describe documentation, not compiled integrations. Download counts refresh daily and are not unique users.
Contributing · Development · Security · Roadmap · MIT license
Backend integration guidance: choose a service and review auth, data and security boundaries.
Optional provider commands
Use ios-agent-mcp environment to inspect the actual Xcode/SDK/simulator inventory.
ios-agent-mcp ai models and ai doctor inspect the dated catalog and account/local availability.
Text generation defaults to on-device Apple models; cloud providers and fallback require explicit configuration.
Provider setup, handoff, simulator CLI and limits. These commands do not replace the coding client or claim autonomous app completion.
Local Apple documentation
Install the archive in Xcode → Settings → Components → Developer Documentation. Read it through Window → Developer Documentation (Shift–Command–0 with standard key bindings). This integration uses xcrun mcpbridge; the archive stays managed by Xcode.
Use xcode-mcp tools for discovered Xcode schemas and doctor xcode for setup diagnostics.
Use ios-agent-mcp docs status and ios-agent-mcp docs symbol SwiftUI.NavigationStack for version-aware documentation grounding. The adapter prefers Xcode MCP DocumentationSearch, then bounded SDK evidence. Apple’s archive is never bundled. Bridge authorization is required; retrieval is not automatic code validation. Setup, tools and limitations.
Experimental native source import
The feature-branch App IR prototype imports a bounded local HTML screen into a validated, source-mapped representation and generates native SwiftUI. It reuses the existing Xcode and simulator tooling. Unsupported markup is reported and blocks generation. This is not universal framework conversion and is not included in npm 2.10.2. See the architecture and roadmap and real native prototype evidence.
Experimental native conversion work, including the static React subset and saved-evidence review, is documented in the Universal App Engine architecture. These prototypes do not establish general React/Next.js compatibility or accepted visual fidelity.
Available Tools
36 toolsanalyze_swift_projectAnalyze a Swift projectA
Produce an overview of a Swift project — file and line counts, deployment target, Swift tools version, frameworks in use, whether tests exist — together with a summary count of findings across every rule category (concurrency, architecture, SwiftUI, availability, App Store). Use this first when you are unfamiliar with a codebase, then run the focused tools on whichever category has findings.
Inputs: path (required).
audit_app_store_readinessAudit App Store submission readinessA
Check a Swift project for issues that cause App Store rejection or runtime termination: permission-gated frameworks used without an Info.plist purpose string, a missing PrivacyInfo.xcprivacy manifest, unlocalized user-facing strings, icon-only buttons with no accessibility label, and print() used for logging. Use before submitting to App Review.
Inputs: path (required).
build_projectBuild an Xcode project or workspaceA
Run xcodebuild build for a project or workspace. Use before installing and launching the app. Requires a scheme and either project or workspace.
Inputs: scheme (required), project, workspace, destination, +2 more.
check_availability_guardsCheck iOS availability guardsA
Verify that version-gated Apple APIs are guarded on the version where they were INTRODUCED rather than the newest SDK. Catches both missing guards and over-restrictive ones — for example Liquid Glass (iOS 26) guarded at iOS 27, which silently drops every iOS 26 device to the fallback. Also flags Foundation Models used without a runtime SystemLanguageModel.availability check. Use before shipping, or after bumping an SDK.
Inputs: path (required). Returns: score, counts, issues, summary, +2 more
create_appA
Create an editable Swift app starter, implementation brief and optional XcodeGen specification/icon layers. Writes a NEW project; does not implement the full app idea. Then use source retrieval, review and simulator tools to implement and verify it.
Inputs: name (required), brief (required), directory (required), xcodegen.
get_apple_technologyRead Apple technology guideARead-onlyIdempotent
Get a compact technology overview and local source routes by default. Use view full only when the entire guide and API topic map are required.
Inputs: id (required), view.
get_apple_updatesFind Apple updates and release notesARead-onlyIdempotent
Search dated Apple update and release-note landing pages with version-specific source links. Does not claim live results.
Inputs: limit, query.
get_reference_outlineOutline a local guideARead-onlyIdempotent
Get heading offsets so only the relevant section needs to be read.
Inputs: path (required).
install_appInstall an app bundleA
Install a built .app bundle into a simulator using xcrun simctl install. Use after build_project or after locating a derived-data app bundle.
Inputs: udid (required), appPath (required).
launch_appLaunch an installed appA
Launch an installed app in the simulator by bundle identifier. Optional arguments are passed after the bundle id and are useful for UI-test/debug launch flags.
Inputs: udid (required), bundleId (required), args.
lint_skillLint an Agent Skill repositoryA
Validate the metadata of an Agent Skill repository rather than Swift source: SKILL.md frontmatter (required keys, kebab-case name, semver version, description length limits), subagent definitions in .claude/agents/ (name matches filename, unknown tool names, and read-only agents that are nonetheless granted Edit or Write), whether generated mirror files such as CLAUDE.md and AGENTS.md have drifted from SKILL.md, and backtick-quoted doc paths that do not resolve. Use when authoring or reviewing a skill, before publishing a release, or when a subagent or skill is not being invoked as expected.
Inputs: path (required).
open_deep_linkOpen a deep linkA
Open a URL in the simulator using xcrun simctl openurl. Use to verify deep links, universal links, onboarding routes, and state restoration.
Inputs: url (required), udid (required).
plan_app_iconPlan layered Icon Composer artworkARead-onlyIdempotent
Return a separate-layer icon specification, Apple workflow and appearance checks. Does not fabricate a native .icon document.
Inputs: appName (required), concept (required).
plan_ios_appPlan an iOS app from a briefARead-onlyIdempotent
Return an implementation workflow and safe CLI argument array for a named app. No files are created and no build is claimed.
Inputs: name (required), brief (required).
prepare_issue_reportARead-onlyIdempotent
Prepare a LOCAL issue preview for an ios-agent-mcp failure, not a defect in the user app. Accepts fixed categories only, never source, logs, paths or credentials. Makes no network requests or submissions. Show the complete preview to the user; opening a link or submitting requires their approval. GitHub sign-in is required to submit. Do not repeatedly suggest a report after dismissal.
Inputs: feature (required), symptom (required), client, platform, +1 more.
read_local_referenceRead local source or guideARead-onlyIdempotent
Read exact bundled file content in bounded character ranges. Use nextOffset to continue without omission; no network or user filesystem access. Offset is a JavaScript UTF-16 string index.
Inputs: path (required), offset, maxChars.
review_app_intentsReview App Intents integrationARead-only
Review SiriKit/INIntent migration opportunities and, when explicitly requested, missing Apple Intelligence entity schemas or onscreen entity associations. Findings are heuristic advisories, not blanket deprecations or proof of invalid code. Use when integrating Siri, Shortcuts or Apple Intelligence.
Inputs: path (required), onscreenContent, appleIntelligence. Returns: score, counts, issues, summary, +2 more
review_swift_architectureReview iOS architecture boundariesA
Check a Swift project for architecture and testability defects: dependencies defaulting to live implementations, the presentation layer naming concrete data-layer types (URLSession, APIClient, ModelContext), singletons resolved inside view models, the domain layer importing UI frameworks, nested NavigationStacks, and deprecated NavigationView. Use when reviewing MVVM or Clean Architecture code, or when a screen cannot be previewed without a network.
Inputs: path (required). Returns: score, counts, issues, summary, +2 more
review_swift_concurrencyReview Swift concurrency and actor isolationA
Check a Swift project for Swift 6 concurrency and isolation defects: @Observable types missing @MainActor, Task.detached, DispatchQueue.main.async in async code, @unchecked Sendable, nonisolated(unsafe), unstructured Tasks in onAppear, empty catch blocks, and types named Task that shadow _Concurrency.Task. Use when reviewing Swift code, migrating to Swift 6, or diagnosing a data race.
Inputs: path (required). Returns: score, counts, issues, summary, +2 more
review_swift_memoryReview memory and retain cyclesA
Check a Swift project for retain cycles and lifetime defects: repeating Timers and block-based NotificationCenter observers capturing self strongly, Combine sinks stored in a cancellables set owned by the same object, non-weak delegate properties, stored closure properties capturing self, unowned self in escaping closures, and long-running unstructured Tasks that keep an object alive after its screen is gone. Use when memory grows over time, when deinit is never called, or before shipping a screen with timers or subscriptions.
Inputs: path (required). Returns: score, counts, issues, summary, +2 more
review_swift_performanceReview SwiftUI and Swift performanceA
Check for runtime cost that shows up as dropped frames: DateFormatter and JSONDecoder allocated inside body, collections sorted or filtered on every render, ForEach over indices instead of stable identity, non-lazy stacks inside a ScrollView, AsyncImage with no frame, blocking file or network I/O on the render path, and GeometryReader wrapping an entire body. Use when scrolling stutters, launch is slow, or before shipping a list-heavy screen.
Inputs: path (required). Returns: score, counts, issues, summary, +2 more
review_swift_securityReview iOS securityA
Check a Swift project for security defects: hardcoded API keys, tokens, and passwords in source; credentials written to UserDefaults instead of the Keychain; App Transport Security disabled; cleartext http:// endpoints; TLS server trust accepted without evaluation; MD5 and SHA-1; Keychain items with over-permissive accessibility; non-cryptographic randomness used for nonces and salts; secrets written to logs; and string interpolation into evaluated JavaScript. Use before shipping, during a security review, or when handling credentials.
Inputs: path (required). Returns: score, counts, issues, summary, +2 more
review_swift_testingReview test suite qualityA
Check a Swift test suite for defects that make it unreliable or vacuous: tests that wait by sleeping, tests with no assertion at all, await inside an XCTAssert autoclosure (which does not compile), live URLSession calls in tests, try!, static mutable state that makes results order-dependent, long expectation timeouts covering for races, and XCTAssertTrue on an equality that hides both values on failure. Also reports when a project has no tests or very few. Use when tests are flaky, before trusting a green suite, or when adding coverage.
Inputs: path (required). Returns: score, counts, issues, summary, +2 more
review_swiftuiReview SwiftUI views and stateA
Check SwiftUI code for view and state defects: fixed font sizes and heights that break Dynamic Type, AnyView, deprecated .cornerRadius, literal spacing values instead of design tokens, materials applied over solid backgrounds, transient presentation state stored on models, legacy ObservableObject and @EnvironmentObject, and try!. Use when reviewing or building SwiftUI screens.
Inputs: path (required). Returns: score, counts, issues, summary, +2 more
run_testsRun Xcode testsB
Run xcodebuild test for a project or workspace. Use to verify runtime/test behavior before visual review. Requires an explicit destination.
Inputs: scheme (required), destination (required), project, workspace, +2 more.
screenshotCapture a simulator screenshotA
Capture a simulator screenshot to a PNG path using xcrun simctl io screenshot. Use as evidence for visual review and before/after comparison.
Inputs: udid (required), outputPath (required), includeImage.
search_apple_technologiesSearch Apple technologiesARead-onlyIdempotent
Find Apple frameworks, tools, services and legacy technologies in the bundled 405-entry source snapshot.
Inputs: query (required), limit.
search_local_referencesSearch bundled source and guidesBRead-onlyIdempotent
Search complete repository guides, Swift source, templates and assets offline. Returns compact file matches without loading bodies. Source files and guide code blocks have different verification status.
Inputs: query (required), kind, limit.
simulator_bootBoot an iOS simulatorA
Boot a simulator by UDID using xcrun simctl boot. Use before install_app, launch_app, screenshot, or open_deep_link. This does not erase or reset simulator content.
Inputs: udid (required).
simulator_environmentInstalled Xcode and device supportA
Report selected Xcode, installed runtimes and real device profiles, including Duo when installed. Does not download or update Xcode.
Inputs: no named parameters.
simulator_listList available iOS simulatorsA
List available Simulator devices using xcrun simctl. Use before booting, installing, launching, or capturing screenshots when you do not know the simulator UDID.
Inputs: no named parameters.
simulator_preview_startOpen sidebar simulator previewA
Start a token-protected loopback screenshot viewer for a booted device. Open the returned URL in the client sidebar/browser. Read-only visual preview; interact in the native Simulator. Not a public hosted simulator.
Inputs: udid (required).
simulator_preview_stopClose simulator previewA
Stop this server’s preview for a device and remove its temporary screenshots; leaves the Simulator running.
Inputs: udid (required).
simulator_showShow native SimulatorB
Boot and wait for a selected available device, then open its native Simulator window for touch/keyboard interaction.
Inputs: udid (required).
simulator_shutdownShut down an iOS simulatorA
Shut down a simulator by UDID using xcrun simctl shutdown. Use after runtime validation to clean up a booted simulator. This does not erase content.
Inputs: udid (required).
terminate_appTerminate an appA
Terminate a running simulator app by bundle identifier without uninstalling it or resetting its state.
Inputs: udid (required), bundleId (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 36 tools
Most tools target a distinct action or review category, and the review_swift_* family is well separated by concern. Some potential confusion exists between simulator_show and simulator_boot, and between search_apple_technologies and search_local_references, but descriptions mostly resolve this.
The dominant verb_noun snake_case pattern is clear and predictable, e.g. install_app, launch_app, build_project, run_tests. A few tools break the pattern, such as simulator_environment, simulator_preview_start/stop, and lint_skill, but these are minor deviations.
36 tools is well above the 25-tool threshold and creates real selection overhead for an agent. The tools cluster into sensible groups, but the sheer number makes the surface feel heavy for what is ultimately an iOS development and review assistant.
The surface covers project analysis, targeted Swift reviews, build/test, simulator lifecycle, previews, app creation, planning, and reference lookup. Minor gaps such as uninstall_app, simulator content reset, or source-editing tools are not critical but keep this from a perfect score.
Maintenance
Related MCP Connectors
Cloud iPhones and Macs with Xcode for AI agents: build, run and test iOS apps, use the screen.
Cloud iPhone Simulators for AI agents: build the Xcode project, read the screen, tap by label, test.
Build, run, and inspect iOS apps in disposable hosted Simulators from cloud coding agents.
The cloud Mac alone, with Xcode, for AI agents: run commands, build and test, use the screen.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to build, test, run, and manage Apple platform projects (iOS, macOS, tvOS, watchOS, visionOS) directly through Xcode. Provides comprehensive control over Xcode projects, Swift packages, simulators, and development workflows without leaving your editor.53MIT
- FlicenseNot gradedqualityNot gradedmaintenanceProvides AI agents with instant access to official Apple developer documentation, Swift programming guides, design guidelines, and Apple Developer YouTube content including WWDC sessions. Uses advanced RAG technology with semantic search and AI reranking to deliver accurate, contextual answers for Apple platform development.7-
- AlicenseNot gradedqualityDmaintenanceGives AI agents the ability to interact with iOS simulators through 21+ tools for mobile app testing.10,447 npmMIT
- AlicenseNot gradedqualityBmaintenanceConnects AI coding clients like OpenCode, Codex, and Claude Code to Xcode and Apple development tools, enabling builds, tests, simulator and device management, profiling, asset handling, and more through natural language.95 npm1MIT