MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
👻 Ghostfox — the browser that can SEE: Gecko-native agent browser. 71 MCP tools, unhookable a11y/compositor vision, captcha solvers, page_download, Android dial-out, visual QA for AI-built UIs.
npm MIT ★ 19 -
Stable since v1.0.0 — MCP server + cross-host agent skill (Claude Code / Codex / OpenClaw / Hermes) for QA testing across pytest / Jest / Cypress / Go / Maestro / Schemathesis / Newman, plus v1.1 Edge AI Runner (RTSP + YOLO). 22 frozen tools, bilingual EN/zh-TW QA knowledge, AI Visual Challenge Solver (reCAPTCHA / hCaptcha), OWASP API Top 10 (2023) scanner, universal qa_plan + verify bookend across 5 core tools (AI 測試大師)
pypi MIT -
Local-first, add-on-free MCP asset QA for headless Blender: executable discovery, bounded background scripts, structural FBX reimport checks, and four-view visual verification
npm MIT -
argusqa-osgithub.com/ironclawdevs27/argusupdated this year
Argus — the QA layer for AI-assisted development. Claude-native (MCP) Chrome audits across 67 categories — errors, visual regressions, a11y, security, performance — no test files, secrets redacted by default (Aegis).
npm MIT -
pursrgithub.com/0xheycat/pursrupdated this year
Visual QA, browser automation, accessibility auditing, screenshot diffing, and MCP tooling for coding agents.
MIT ★ 2 -
Production-grade MCP (Model Context Protocol) server integrating Gemini for looped web research, image generation, visual QA, and codebase docs.
★ 1 -
MCP server for OmniSnap AI Studio. Gives AI agents stability-scored test selectors, design tokens, visual captures and QA diagnostics from your real, logged-in browser session.
npm MIT -
Design engineering for AI agents: MCP server + agent skills that give Claude Code, Cursor, Codex, OpenCode, Antigravity and Windsurf a UI/UX design expert, site design DNA, motion mechanics and live Chromium visual QA (accessibility, Core Web Vitals).
npm MIT -
Autonomous QA scanner: point it at your running app and it walks the real user flows in a headless browser and reports what's actually broken: broken pages/links, console and network errors, empty/placeholder data, broken forms, state-loss, bad loading/er
npm Apache-2.0 -
Lastest Visual Regression Testing - Cloud/Self-hosted version
NOASSERTION ★ 22 -
VFA — Visual & Functional Auditor: auditoria web autonoma (visual + funcional) expuesta como servidor MCP, con Playwright local y motor universal LiteLLM.
pypi LicenseRef-Proprietary -
Uiprobe plugin for Claude Code: a check Claude can run against your Figma design. It compares the built page with the frame, value by value, and Claude fixes the differences.
MIT -
Uiprobe plugin for ChatGPT and Codex: a check your agent can run against your Figma design. It compares the built page with the frame, value by value, and the agent fixes the differences.
MIT ★ 1 -
Local MCP server that compares a mobile app screen (Android or iOS Simulator) with its Figma design
MIT -
A Codex plugin and local MCP runtime for context-bounded image generation and inspection.
Apache-2.0 ★ 97 -
@perpetio/redlineactive
A review layer for any website, built for coding agents. Reviewers comment on the live page; Claude Code, Codex or Cursor reads each comment over MCP with the exact element, fixes it and resolves it. One script tag, no dependencies.
npm SEE LICENSE IN LICENSE -
mcp-image-scientificgithub.com/tofunori/mcp-image-scientificupdated this year
MCP server for publication-quality scientific figures — diagrams, charts, maps with QA validation. Powered by Gemini.
MIT ★ 1 -
Playwright end-to-end testing MCP server — run, debug and inspect E2E tests from any AI agent: failure analysis, live DOM inspection, selector validation, visual diffs, flaky-test diagnosis.
MIT -
Figures of protein structures, sequences, contact maps, pipelines and plots for papers: an HTML page kit printed to vector PDF and PNG, flat ChimeraX renders, QA checks, and a Claude Code skill, hooks and MCP server.
NOASSERTION ★ 3