"Assistance with macOS Spaces feature" matching MCP servers:

An MCP server for probing which user-interaction features a client actually supports — form and URL elicitation, multi-step wizards, sandboxed MCP App UIs, file return/upload, progress, logging and cancellation, plus client capability inspection — over stdio and Streamable HTTP on both protocol generations.

Enables evaluation of patent feature-separation results by listing records, checking alignment with claims and original text, and running deterministic quality gates plus a Judge audit.

Enables Claude to inspect and drive native macOS app UIs during development via an in-process view tree and screenshot renderer, without requiring screen recording permission.

Enables users to analyze already-persisted single-patent evaluations to discover cross-patent batch issues such as language, technical-domain, input-structure sensitivity, and language-structure interactions, without modifying existing MCP, ledger, or single-record evaluation JSON.

A local observation-only MCP server for macOS that provides secure, atomic evidence capture with strict target approval and manifest-based output.

Provides a read-only MCP bridge that lets Claude Web inspect workspace files, git state, and recorded test results while Codex remains the sole executor of changes.

An MCP server that allows AI tools like Claude Desktop, Claude Code, and Cursor to visually interact with macOS applications by capturing screenshots and controlling the mouse and keyboard.

Free, MIT-licensed MCP testing harness with Jay: risk-based testing workflows, exploratory and regression checks, accessibility investigation, bug triage, disposable demos, and protected local evidence reports. Runs locally via @testers-ai/carbon-mcp; the coding agent supplies model, browser, and shell access, and analytics defaults off in the npm edition.

Provides a framework for running multiple MCP servers using FastAPI, stdio, and streamable-http transports, with an echo tool for testing and integration with MCP Inspector.

MCP server for screen recording on macOS, iOS Simulator, and Android, with key-frame extraction via ffmpeg, enabling AI agents to capture UI motion and transient visual states.

AI-optimized Vitest interface that provides structured test output, visual debugging context, and intelligent coverage analysis for more effective AI assistance with testing.

Provides AI assistants with visual feedback for responsive web design by capturing screenshots and extracting DOM layout data through the Viewpo macOS app. It enables automated UI verification and responsive behavior comparison across multiple viewport breakpoints.

Godot 4 MCP server with: Test running (GUT/GdUnit4) with structured pass/fail results API docs search with 30+ Godot 3→4 migration mappings Script analysis detecting 10 common GDScript pitfalls Scene/resource file parsing with antipattern detection Viewport screenshot capture LSP diagnostics from Godot's language server TypeScript, cross-platform (macOS/Windows/Linux), published on npm

Auto-generates and manages test cases for any project from feature descriptions, with tools for adding, listing, updating, and exporting test cases via Claude.

One MCP endpoint, 43 tools for iOS-simulator E2E — native UI automation, Maestro flows, trustworthy oracle-ladder assertions, WebView DOM + network (JSON/HAR), and React Native debugging (Metro logs/network/state). macOS + Xcode.

Enables a coding agent to keep one JSON feature specification per feature, governed by a progressive schema, and to render it as editable Markdown documents for a product owner. Answers and direct Markdown edits are reconciled back into the validated model through stdio MCP tools, applying coherent changes and reporting those that widen scope or contradict the model.

Provides intelligent CSS/JS feature compatibility checking with configurable browser targets, polyfill support, and smart project scanning. Enables developers to automatically detect browser compatibility issues and get actionable remediation steps with build tool configurations.

Exposes the macOS Playdate Simulator as typed MCP tools, enabling building, launching, controlling, and capturing the simulator programmatically.

Lets your coding agent control and inspect a live Safari browser on macOS. Provides access to Safari DevTools for debugging, automation, and testing.

Enables AI coding agents to build, run, test, and visually inspect Garmin Connect IQ apps by automating the macOS simulator with deterministic input synthesis, log streaming, screenshots, and device metadata.

Enables an LLM agent to drive a real iPhone (iOS 27+) over USB from Windows, Linux, or macOS with nothing installed on the phone, reading the foreground app's accessibility tree as a numbered element list and injecting HID touches, swipes, and keyboard/paste text while waiting on video frames to settle. Each action returns the refreshed element list, giving one round trip per step.

Provides a reference MCP server that implements every MCP feature so client, gateway, and runtime authors can test against a single endpoint, and publishes a service contract describing its capabilities.

Enables AI agents to control a hardened, human-like Chromium browser for automation and testing, with ad blocking, natural mouse movements, and Cloudflare Turnstile assistance.

Enables extracting only the minimal AST closure for a target feature from GitHub, local, package-registry, or bundled JavaScript references, replacing third-party dependencies with zero-dependency shims and adapting the code to a host project's language and style. It also generates runnable parity tests that verify 1:1 behavioral equivalence via Golden I/O vectors.

A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

Enables analysis of Karate framework feature files, extracting dependencies and generating interactive dependency graphs.

Provides comprehensive React Native development assistance with expert-level automated code remediation, security vulnerability fixes, performance optimization, and production-ready code generation. Includes testing suite generation, dependency management, and accessibility compliance tools.

A comprehensive MCP server for iOS/macOS development that gives AI assistants full control over Xcode build, test, simulator management, and app deployment.

Enables AI coding agents to request, check the status of, or withdraw a trial of a service virtualization platform, read agent-oriented documentation and trial onboarding guidance, and submit feature requests or feedback, all without an API key.

MCP server for operating and testing Android devices with AI agents. Provides observation and action tools for interactive control and spreadsheet-driven test runs.

Enables safe evaluation of trading-oriented MCP tools through a no-execution stdio mock with read-only signal listings, deterministic paper previews, and confirmation requests that always fail closed.

Lets any MCP client build and test native iOS or macOS apps with xcodebuild and XCTest, then launch the app on a cloud Mac's simulator and inspect the screen, tap, type, swipe, and press buttons to verify its own work. Also returns a live browser link for watching and using the running app.

Enables agents to read and create feature specs, track coverage and status, and generate pytest test skeletons from specs without leaving the conversation.

Enables LLMs to automate browsers and interact with web pages using structured accessibility snapshots rather than screenshots or vision models.

Verification browser for coding agents. Headless-by-default WebKit windows with DOM eval, screenshots, pixel-diff with a real match percentage and heatmap, and live hand-off to a human. One static binary, no Chromium.

A TypeScript MCP server delivering a vendored 'dangerous skills' corpus and adversarial fixtures over MCP for security-research testing, supporting SEP-2640 skill delivery with archive-safety hardening.

Enables headless debugging of Windows executables from Linux/macOS hosts by orchestrating winedbg's gdbserver and a GDB client, exposing 19 tools for launch, attach, breakpoints, stepping, register/memory access, and session lifecycle.

Enables interaction with Kiwi TCMS test management system through MCP, supporting read and write operations on test plans, cases, runs, and executions, with API key authentication.

Enables AI agents to compare database tables using read-only tools, with credentials managed locally and never exposed to the model.

Exposes data validation as tools so an AI agent can check whether data is actually correct before using it, scoring CSV files with per-row problem details, catching impossible dates, inferring schemas, and generating readable reports.