
Claude Desktop
Desktop · Freemium · Proprietary
Anthropic's official Claude AI desktop application. Supports MCP servers to extend functionality.
Developer Tools · OS Automation

lapfelix/XcodeMCP
Using with Apple's Official Xcode MCP: Apple now provides an official Xcode MCP server. XcodeMCP can run alongside it in sidekick mode (--sidekick-only), providing complementary tools like project management and XCResult analysis. In a future version, XcodeMCP will transition to sidekick-only mode by default.
npx -y xcodemcp@latest{
"mcpServers": {
"xcodemcp": {
"command": "npx",
"args": [
"-y",
"xcodemcp@latest"
]
}
}
}XCODE_MCP_PREFERRED_SCHEMEXCODE_MCP_PREFERRED_XCODEPROJXCODEMCP_LOG_FILEXCODEMCP_CONSOLE_LOGGINGBrowse Results: Navigate through test hierarchies, view pass/fail status, and examine detailed test information
Console Logs: Extract console output and test activities with precise timestamps for debugging
Quick Summaries: Get overview statistics including pass rates, failure counts, and duration
Screenshot Extraction: Extract PNG screenshots from test failures using ffmpeg frame extraction from video attachments
Timestamp Precision: Specify exact timestamps to capture UI state at specific moments during test execution
AI-Readable Format: Extract UI hierarchies as compressed JSON with single-letter properties (t=type, l=label, f=frame, c=children, j=index)
Timestamp Selection: Automatically find the closest UI hierarchy capture to any specified timestamp
Element Deep-Dive: Use index references to get full details of any UI element, including accessibility properties and frame information
Size Optimization: 75%+ size reduction compared to full hierarchy data while maintaining all essential information
xcode_build
build
xcode_test
test
xcode_build_and_run
build-and-run
xcode_health_check
health-check
xcresult_browse
xcresult-browse
find_xcresults
find-xcresults
xcode_open_project
Open projects and workspaces
xcode_get_workspace_info
Get workspace status and details
xcode_open_file
Open files with optional line number
xcode_clean
Clean build artifacts
xcode_debug
Start debugging session
xcode_stop
Stop current operation
xcode_set_active_scheme
Switch active scheme
xcresult_browser_get_console
Get console output for specific tests
xcresult_summary
Quick overview of test results
xcresult_get_screenshot
Extract screenshots from test failures
xcresult_get_ui_hierarchy
Get UI hierarchy as AI-readable JSON with timestamp selection
xcresult_get_ui_element
Get detailed properties of specific UI elements by index
xcresult_export_attachment
Export specific attachments from test results
Details on this page are taken from the project's README. Open README
Clients mentioned in this server's README:

Desktop · Freemium · Proprietary
Anthropic's official Claude AI desktop application. Supports MCP servers to extend functionality.
Desktop · Freemium · MIT
VS Code integrates MCP with GitHub Copilot through agent mode, allowing direct interaction with MCP-provided tools in your agentic coding workflow. Configure servers in Claude Desktop, workspace, or user settings, with guided MCP installation and secure handling of secrets in input variables to avoid leaking hardcoded keys.

microsoft/playwright
Playwright is a framework for web automation and testing. It drives Chromium, Firefox, and WebKit with a single API — in your tests, in your scripts, and as a tool for AI agents.

yamadashy/repomix
Repomix is a tool that packs a codebase into an AI-friendly format, supporting local and remote repository processing and providing code compression, security checks and multiple output formats.

bytedance/UI-TARS-desktop
TARS is ByteDance's multimodal AI agent stack, shipping two projects: Agent TARS (a CLI and Web UI agent built on MCP) and UI-TARS-desktop (a desktop GUI agent).

ahujasid/blender-mcp
formerly blender-mcp — the PyPI package is now mcp-for-blender. Existing setups keep working; no config change is required. Read more.

microsoft/playwright-mcp
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.

comet-ml/opik
Opik is the open-source LLM observability and evaluation platform for AI agent tracing, LLM evaluation, prompt management, and production monitoring. Built by Comet. Apache-2.0 licensed, free to self-host the full platform, with 20,000+ GitHub stars.