For benchmarking Xcode builds, XcodeBuildMCP is the direct fit: it is an MCP server and CLI that lets AI agents build, test and run iOS/macOS projects in Xcode 1. Apple's Xcode page 2 does not describe build tooling, so it is left out; the request does not state a platform or constraint beyond Xcode, so no question is needed.
- 1
XcodeBuildMCPxcodebuildmcp.comwebsite read, tools not yet checked
An MCP server and CLI that gives AI agents control over Xcode to build, test and debug iOS and macOS apps, which can drive repeated Xcode builds for benchmarking 1.
official:package · xcodebuildmcp
- 2
Sentrysentry.ioverified and signed
Application performance monitoring that traces performance, with an official MCP server and CLI, which can capture build and runtime timings for an Xcode project 3.
official:MCP server · @sentry/mcp-serverSDK · @sentry/nodeCLI · sentry-clirepository · sentry-pythonskill · sentry-cli+49 community tools built for it
for agents: xcodebuildmcp · xcodebuildmcp-cli · sentry-snapshots-cocoa
- 3
Sources
- 1MobileBuildMCP - AI-Powered Xcode Automationmobilebuildmcp.com · read 2026-10-29
- 2Appleapple.com · read 2026-10-29
- 3Sentry Docs | Application Performance Monitoring & Error Tracking Softwaredocs.sentry.io · read 2026-10-29
- 9fastlane - App automation done rightfastlane.tools · read 2026-10-29
For agents: the 10 actions behind this answer
· Xcodebuildmcp website read, tools not yet checked
Let AI assistants build, test, and debug your iOS apps autonomously. MobileBuildMCP bridges the gap between AI agents and Xcode.
· Apple Xcode Select website read, tools not yet checked
Discover the innovative world of Apple and shop everything iPhone, iPad, Apple Watch, Mac, and Apple TV, plus explore accessories, entertainment, and expert device support.
xcodebuildmcp · xcodebuildmcp verified and signed
Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
benchmark-checklist · benchmark-checklist verified and signed
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
createPreviewBuild · Cloudflare API verified and signed
Create preview build
· SWE-bench Leaderboards website read, tools not yet checked
build · ninja verified and signed
agents-sdk · agents-sdk verified and signed
Build, debug, or review Cloudflare Agents SDK applications using the agents package.
record_deepdive_extras · agent-health found in code, not yet checked
Call this AT MOST ONCE, near the end of your investigation, after you have queried both runs.
· fastlane website read, tools not yet checked
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.