githubinferredactive
SilbercueSwift
provenance:github:silbercue/SilbercueSwift
WHAT THIS AGENT DOES
SilbercueSwift helps AI tools work much more effectively with iOS apps (like iPhones and iPads). It solves the problem of AI struggling to understand the complex information generated when building and testing these apps – things like error messages and screenshots. Developers and businesses using AI to automate iOS app development and testing will find SilbercueSwift significantly speeds up their workflows and improves the accuracy of their AI assistants.
README
# SilbercueSwift [](https://github.com/silbercue/SilbercueSwift/releases) [](https://github.com/silbercue/SilbercueSwift#free-vs-pro) [](https://polar.sh/silbercueswift) [](https://opensource.org/licenses/MIT) [](https://registry.modelcontextprotocol.io) []() [](https://swift.org) The fastest, most complete MCP server for iOS development. One Swift binary, 58 tools, zero dependencies. **SilbercueSwift has the most complete toolset of any alternative out there.** Built for [Claude Code](https://claude.ai/claude-code), [Cursor](https://cursor.sh), and any MCP-compatible AI agent. > **Looking for an alternative to existing iOS MCP servers?** SilbercueSwift covers the full feature set of XcodeBuildMCP, Appium-MCP, and iosef in a single binary — plus xcresult parsing, UI automation, code coverage, and up to 75x faster screenshots. [See comparison below](#comparison-with-other-mcp-servers). ## Why SilbercueSwift? Every iOS MCP server has the same problem: **raw xcodebuild output is useless for AI agents.** 500 lines of build log, stderr noise mistaken for errors, no structured test results. Agents waste minutes parsing what a human sees in seconds. SilbercueSwift fixes this. It parses `.xcresult` bundles — the same structured data Xcode uses internally — and returns exactly what the agent needs: pass/fail counts, failure messages with file:line, code coverage per file, and failure screenshots. | What you get | XcodeBuildMCP | Appium-MCP | iosef | SilbercueSwift | |---|---|---|---|---| | Screenshot latency | ~1127ms | ~77ms | ~83ms | **~316ms**<br>(<img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> **~15ms**, 75x) | | View hierarchy | ~259ms | ~938ms | ~44ms | **~31ms**<br>(<img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> **~5ms**) | | Find element | — | 76ms | 50ms | **31ms**<br>(<img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> **<1ms** + auto-scroll) | | Tap (coordinates) | 235ms | 470ms | 48ms | **16ms**<br>(<img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> **4ms**) | | Swipe | 1284ms | 2685ms | 262ms | **~250ms** | | Build for simulator | Yes | — | — | **Yes** | | Build + Run in one call | Yes (sequential) | — | — | **Yes (parallel, ~9s faster)** | | Structured test results | Partial | — | — | **Full xcresult JSON** | | Failure screenshots from xcresult | — | — | — | **Auto-exported** | | Code coverage per file | Basic | — | — | **Sorted, filterable** | | Build error diagnosis | stderr parsing | — | — | **xcresult JSON with file:line** | | Navigate (find + tap + verify) | — | — | — | **1 call (~380ms)** | | Double tap | — | — | — | **~60ms** | | Drag & drop | — | Coordinates only (3 calls) | — | **Element-to-element (1 call)** | | Scroll to element | — | Manual swipe loop | — | **SmartScroll (1 call)** <img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> | | Alert handling | — | Single alert | — | **3-tier search + batch accept_all** <img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> | | iOS 18 ContactsUI dialog | — | — | — | **Supported** | | Batch UI automation | — | — | — | **run_plan: multi-step plans with adaptive decisions** | | Log filtering | Subsystem only | — | Partial | **Topic-filtered: 90% fewer tokens** <img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> | | Console log per failed test | — | — | — | **Optional** | | Wait for log pattern | — | — | — | **Regex + timeout** | | Visual regression | — | — | — | **Baseline + pixel diff** <img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> | | Multi-device check | — | — | — | **Dark Mode, Landscape, iPad** <img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> | | Cross-platform (Android) | — | Yes | — | — | | Tools | 77 (Rust) | 61 (Node.js + Appium) | 15 (Swift) | **58 (Native Swift, 8.5MB)** | | Cold start | ~400ms | ~1000ms | ~100ms | **~50ms** | ### Where SilbercueSwift really shines >  **Screenshots up to 75x faster** — ~316ms (<img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> ~15ms) Free tier screenshots (~316ms) are faster than XcodeBuildMCP (~1127ms) and most alternatives. Pro brings latency down to ~15ms — 5x faster than Appium, 75x faster than XcodeBuildMCP. Agents can take screenshots freely without penalty at either tier. >  **Structured test results from xcresult bundles** — zero guesswork on failures When a test fails, the agent gets the error message, the exact file:line, a screenshot of the failure state, and optionally the console output — all parsed from Apple's `.xcresult` format. No guessing from 500 lines of xcodebuild stderr. This is the difference between "agent knows what broke" and "agent guesses what broke". >  **Single binary, zero dependencies** — 58 tools, install in 10 seconds `brew install silbercueswift` — done. 8.5MB native Swift binary. No Node.js, no npm, no Appium server, no Python, no Java, no Rust toolchain. Cold start in ~50ms. The fastest way to get an iOS MCP server running. >  **Agent reads only what matters — 90% fewer tokens, zero wasted calls** (topic filtering <img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center">) Free tier already strips noise: 15 known noise processes are excluded at capture time, and duplicate lines are collapsed (79% I/O reduction). Pro adds topic filtering — `read_logs` categorizes lines into 8 topics and shows only app + crashes by default, with a menu: `network(87) lifecycle(12) springboard(8)`. The agent opens specific topics in one call — no guessing, no iteration. >  **One call to dismiss all permission dialogs** — 3 alerts in 1 roundtrip <img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> Every app shows 2–3 permission dialogs on first launch. Other servers require the agent to screenshot → find button → click, per dialog. `handle_alert(action: "accept_all")` clears them all in a single call, searching across SpringBoard, ContactsUI, and the active app. Free tier handles alerts individually with `accept` / `dismiss`. >  **Drag & drop with element IDs** — 1 call instead of 3 <img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> "Drag item A above item B" is a single call: `drag_and_drop(source_element: "el-0", target_element: "el-1")`. The competition only supports raw coordinates, forcing the agent to find both elements, extract their frames, and build a W3C Actions sequence — 3 calls minimum. >  **Auto-scroll to off-screen elements** — no more manual swipe loops <img src="https://img.shields.io/badge/Pro-blueviolet?style=flat-square" align="center"> `find_element(using: "accessibili [truncated…]
PUBLIC HISTORY
First discoveredMar 28, 2026
IDENTITY
inferred
Identity inferred from code signals. No PROVENANCE.yml found.
Is this yours? Claim it →METADATA
platformgithub
first seenMar 27, 2026
last updatedMar 27, 2026
last crawled20 days ago
version—
README BADGE
Add to your README:
