"Git for Windows" matching MCP servers:

Enables AI clients to query and operate Git for a Cocos Creator 3.8 project and its submodules, drive editor asset/scene/prefab tools, and inspect the running preview's hierarchy, properties and page events through a scoped, token-gated bridge that previews every write as a one-time plan and never executes arbitrary code.

Enables users to query, create, update, and manage Digital.ai Agility assets through MCP tools, with secure Windows Credential Manager authentication and configurable write operations.

Enables AI agents to control and interact with the Windows operating system, including file navigation, application control, UI automation, and QA testing.

Enables AI agents to seamlessly integrate with the Windows operating system, performing tasks such as file navigation, application control, UI interaction, and QA testing via the MCP protocol.

Fail-closed merge gate for AI coding agents: verify_repo runs the tests that existed before the change against a git working tree and answers MERGE, BLOCK or INCONCLUSIVE. The agent names what to judge; the operator pins the baseline and the floors.

An MCP server that enables Claude Code and other MCP clients to take screenshots of the full screen or specific windows, with support for repeated captures over intervals.

Local, deterministic review of Git changes for coding agents: weakened tests and CI gates, security-boundary changes, input-to-sink flows, and blast radius. Runs the RepoPilot Rust CLI over stdio; no source leaves the machine and no model is called.

Umbra is the trust layer for AI-generated code. It scores any repo 0-100 with file:line evidence (security, slop, Docker-verified build/boot, and claim receipts that catch agents lying about tests), and guards agent file writes mid-stream blocking leaked keys, alg:none JWTs, and git-hook plants before they land. Tools: scan_repo, guard_content, get_score.

A read-only Model Context Protocol server that converts local Git changes and JUnit XML reports into traceable release evidence, risk findings, and a rollback checklist.

Enables an editor LLM to run only preconfigured lint, test, and read-only git commands, blocking arbitrary bash execution.

Diagnoses HLS and DASH streams by reading manifests over HTTP, checking rendition ladders, segment timing, live windows, and DRM, and reports issues with evidence—no ffmpeg required.

Enables AI agents to safely read, search, and inspect a local git repository, including PR-style diffs and changed-file summaries. It also supports opt-in allowlisted test runs.

Fork, break, and revert real VirtualBox VMs as MCP tools; drive GUI-only guests through the hypervisor (screenshot, click, type, keys) with nothing installed in the guest. Windows host with VirtualBox.

Enables Claude to capture screenshots of the screen, windows, regions, and web pages, and compare screenshots for visual regression testing.

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

Enables AI assistants to interact with TrafficMorph for load-testing and CI-failure triage, including run management, profile lifecycle, and domain verification through natural language.

A reference MCP server that enforces identity-aware tool access using role-based permissions (Reader, Analyst, Auditor) and supports multiple identity routes like Entra RBAC, Copilot Studio, and Okta XAA. It provides read-only access to test evidence with explicit denial paths for unauthorized tools.

Enables AI coding agents to submit work for external review before declaring a task done, receiving evidence-backed fix lists and verdicts based on git-measured changes and calibrated quality scoring.

Read, write, analyze and test the VBA inside Excel, Word, PowerPoint and Access files, and edit the document around it. The file layer needs no Office installation and runs anywhere; running macros and tests needs Windows with Office.

Enables AI assistants to perform comprehensive code reviews of local uncommitted changes by combining git diffs with static analysis from linters like ESLint and TypeScript. Returns structured JSON feedback with findings, suggestions, and quality assessments powered by Google's Gemini CLI.

Windows桌面截图与窗口自动化工具，支持后台操作、不抢焦点，可截取窗口/屏幕、模拟鼠标键盘、点击菜单等。

Local, read-only acceptance reports for AI-assisted Git changes, exposed as one MCP tool and a CLI. It separates Git-visible changes, explicit check evidence, review prompts, and unchecked work without uploading reports or giving a "safe to merge" verdict.

Enables AI coding agents to run fast, sandboxed pre-flight validation—tests, type-checking, linting, security audits, Git safety scans, and fix suggestions—before committing or pushing code, with instant caching and optional Docker isolation.

Provides AI assistants with token-efficient access to Google Play Android Vitals, enabling them to diagnose ANRs, track crashes, analyze startup performance, and compare app versions for release optimizations.

Provides browser automation tools for coding agents—goto, browse, goal, page_state, and summary—so agents can drive real pages through auditable, gated decisions and record traces for offline replay.

Enables AI assistants and local workflows to run Jev-powered tools that judge speeches line by line, audit drafts against goals, bisect hard-to-test bugs, simulate common-sense physics, score note pairs, and ask arbitrary typed questions cheaply.

Provides agents with temporary visual capture of Hyprland/Wayland monitors, windows, or regions as PNGs, enabling visual verification and self-correction of UI and desktop tasks.

Checks the outcome after an agent handoff, when a request, 200 or ack only shows the handoff. Reads one field of one exact public HTTPS JSON record, with a same-site known-good control, for 20-120 s. Returns PROVED, DISPROVED or INCONCLUSIVE with a signed receipt you can verify. 5 free checks, then USD 1 per completed check, by card (Stripe Checkout) or existing Link wallet. INCONCLUSIVE is free.

Enables AI assistants to run Godot unit tests using GUT and read results in a structured format

Delegates test writing to a headless second coding agent in an isolated git worktree, then builds, runs the tests, verifies that only test paths changed, and returns a compact report plus optionally applies the verified tests to your checkout. It also flags failures that point to bugs in the production code rather than the tests, keeping test code and terminal logs out of the main agent's context.

Zero-sidecar MCP server embedded directly in the Godot 4 editor as a GDScript EditorPlugin — no Node or Python sidecar. Reflection-driven tools over any engine class, validate-before-write GDScript, scene/script/resource authoring, and a runtime play-test loop (play, screenshot, input, assert).

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

Enables AI agents to boot fresh, disposable Windows Sandbox machines, copy and run apps, drive their UI with UI Automation, capture screenshots, inspect crashes, and collect reports. It also supports installer testing, offline execution, and detonation of untrusted files through MCP tool calls.

Enables coverage-driven test generation for RHDH plugin forests by analyzing git diffs and coverage reports, recommending the cheapest test layer, and emitting actionable test briefs, including Playwright MCP prompts for UI gaps.

A comprehensive development toolkit with 23 tools covering code quality analysis, development efficiency, and project management. Enables AI-assisted code review, test generation, performance analysis, SQL generation, UI component creation, and automated project documentation.

Enables an agent to run automated binary-search git bisection across a repository's mainline history using isolated git worktrees, pinpointing the commit that introduced a regression without touching the user's working copy. Each candidate is validated by a human-supplied check command, with skip/timeout handling and resumable sessions stored in SQLite.

Enables coding assistants to gather bounded source evidence, prepare typed judgments, and verify claims through MCP tools while leaving editing and execution to the host.

A local Model Context Protocol server that enables MCP clients to control Android, iOS, and Windows devices through AirtestIDE, supporting device listing, screenshots, touch, swipe, key events, and app management.

Frontend expert for Claude Code. Captures screenshots, runs Lighthouse + axe-core accessibility audits + code analysis, generates an expert review, and auto-fixes everything — 12 tools, completely free for Pro plan users.

Lets AI coding agents simulate venues, replay traces through positioning filters, pinpoint error windows and nearby beacons, and A/B test configuration fixes across scenarios on identical seeds. All results come from the engine's own replay and metrics code, so accuracy claims and regressions can be verified rather than guessed from source.