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.
-
@matware/e2e-runnergithub.com/fastslack/mtw-e2e-runnerupdated this year
E2E test runner using Chrome Pool (browserless/chrome) with parallel execution
npm Apache-2.0 -
mtw-e2e-runnergithub.com/fastslack/mtw-e2e-runnerupdated this year
JSON-driven E2E test runner with parallel execution, Chrome pool, and Claude Code MCP integration
Apache-2.0 ★ 7 -
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 -
Task environments for AI agents working on .NET apps, as an MCP server: raise the app with its services on Nomad, call its API, read its logs, run its end-to-end tests, one environment per task. Native AOT ready.
MIT -
Free MCP server and agent skill that runs, diagnoses and fixes failing Playwright tests (TypeScript and pytest), and proves each fix by re-running it. Flaky verdicts, finds the commit that broke a test, blocks fixes that check less, posts CI fixes as PR suggestions, accessibility and Web Vitals audits. MIT, no account.
npm MIT ★ 5 -
The system purpose is to realize a SysML v2 model repository exposing standard APIs and to make the repository accessible through the Model Context Protocol (MCP). The end goal is a curated knowledge base of implemented systems and reusable specification.
GPL-3.0 -
MIT-licensed MCP bridge to the Alethia runtime — the patent-pending zero-IPC E2E test runtime for AI agents. 2-5x faster than Playwright MCP. Signed evidence packs, EA1 fail-closed safety gate, WCAG + NIST 800-53 audits built in. Local-first, zero telemet
npm MIT -
playwright-autopilot-mcpgithub.com/nikolarss0n/playwright-autopilotupdated this year
Autonomous Playwright E2E test debugger MCP server for Claude Code
npm MIT -
Fastest cross-platform E2E Automation for Mobile & Web
Apache-2.0 ★ 103 -
npx launcher for the Testa MCP server (iOS Simulator E2E driver for AI agents). Requires the native `testa` binary — install it with Homebrew.
npm MIT -
QuickCast Screen-to-Action Protocol MCP Server: Automated Bug Reports, Playwright E2E Tests, and SOP Generator from Screen Recordings.
MIT -
Local emulator for E2E testing: fake SMTP, Telegram, WhatsApp, SMS, push, Slack, Discord, Stripe & OAuth with a web timeline and MCP server for LLM agents.
MIT ★ 2 -
MCP server that lets AI see and operate Windows desktops (UI Automation + WebView2 via CDP) and replay saved scenarios for E2E tests. .NET 10.
MIT -
High-performance Model Context Protocol (MCP) server for QuickCast Screen-to-Action Protocol: automated bug reporting, Playwright E2E test scaffolding, and SOP generation from QuickCast recordings.
npm MIT -
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.
MIT ★ 407 -
siteglass-mcpgithub.com/siteglassio/siteglass-mcpupdated this year
MCP server for siteglass.io — agent-driven web QA: register a site, scan it, auto-generate and run E2E test flows, read results + replay. Pay-per-action in credits over Bitcoin Lightning.
npm MIT -
AI-native desktop browser that is also an MCP server. A built-in agent clicks, reads and fills forms for you, and asks before anything that costs money. E2E-encrypted sync, local models via Ollama. Open source (MPL-2.0).
MPL-2.0 -
Zero-token ($0) E2E Playwright QA engine for Claude Code, Google Antigravity & Cursor. Crawls live DOMs into ~1.2k-token accessibility maps, runs self-healing intent plans locally, and compiles to native .spec.ts. Dual-mode: Agent Skill CLI + Stdio MCP Server.
MIT ★ 2 -
podium-mcpgithub.com/hoainho/podium-mcpupdated this year
One MCP server, 51 tools for AI agents on mobile + canvas UIs: iOS & Android automation, Maestro E2E, evidenced assertions, React Native/Metro debugging — plus a no-vision canvas/WebGL brain (Pixi/Konva/Fabric/Phaser/Three/Babylon) that drives game UIs like DOM elements, ~5x cheaper than screenshot loops.
MIT ★ 6 -
periscope-mcpgithub.com/segentic-lab/periscope-mcpupdated this year
Web-app QA, testing & analysis for AI agents — 74 Playwright tools: authenticated flows (2FA/SSO), 25-action E2E workflows, hard assertions, session reports, and accessibility / SEO / GEO / Core-Web-Vitals + Lighthouse audits across a page or a full crawled site. Battle-tested by an AI agent on real apps.
AGPL-3.0 ★ 10 -
Let LLMs author your integration tests—E2E-style.
MIT ★ 10 -
Agent-first E2E testing CLI
MIT ★ 29 -
Askew local connector — MCP server that lets your AI agent use your iPhone through Shortcuts (E2E encrypted relay)
npm MIT -
Let your Claude Code session ask your teammate's Claude Code session questions — E2E encrypted, read-only forks, you approve every answer.
npm MIT ★ 2 -
mindmeld: let your Claude Code session ask a teammate's Claude Code session questions. E2E encrypted, read-only answers, approved in Claude.
npm MIT -
OpenCode Computer Use: local Codex-style visual desktop control for Windows (MCP stdio, 35 tools, DPI-correct, verified E2E)
MIT ★ 3 -
sylex-memorygithub.com/MastadoonPrime/sylex-memoryupdated this year
Persistent encrypted memory service for AI agents — MCP server with E2E encrypted private vaults, shared knowledge commons, community channels, and 23 tools. Free, open source.
-
Persistent memory for AI coding tools, in an open portable format. Sync Claude, Cursor, Gemini, Copilot, Windsurf + 6 more across machines via MCP. E2E-encrypted sync. MIT.
npm MIT ★ 15 -
Unified stdio MCP server for Jira, Confluence, and Bitbucket Data Center — 499 policy-gated REST operations, read-first exposure tiers, E2E-verified against licensed DC instances
MIT -
Your phone, for your AI agents: SMS, OTP codes, contacts and call log for Claude, Hermes, Codex and any MCP client. E2E encrypted, self-hosted relay.
MIT -
Long-term memory for AI agents over plain Markdown: provenance, token-budgeted recall, revertible write-back, and E2E-encrypted multi-device sync. MIT, Rust + TypeScript.
npm MIT -
Enterprise MCP server & CLI toolkit for AI agents: Spec-Driven SDLC, codebase reverse-engineering (/trace), cross-surface SSOT docs, deterministic codegen, and automated Playwright E2E testing.
npm MIT -
Open-source E2E testing an AI agent records for you. Plain-language tests, recorded once on your real app (web, desktop, SAP, Citrix, AI agents), replayed on every commit with zero LLM calls.
npm Apache-2.0 ★ 6 -
An MCP Server for Android running on the phone, optmized for token usage, supports also files downloads, camera, a privacy mode (to anonymize/pseudononymize your PII) and support various tunnelling (included a free E2E HTTPS tunnel out of the box in addition to cloudflare and ngrok).
NOASSERTION ★ 837 -
MCP server for React Native and Expo development
npm SEE LICENSE IN LICENSE -
glancegithub.com/DebugBase/glanceupdated this year
AI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your terminal.
MIT ★ 158 -
Acceptance test agent for coding agents: real-browser tests, with screenshots on the PR.
npm Apache-2.0 -
The independent local harness for AI-repaired Playwright tests — it runs the tests itself, so a green run can't be faked.
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 -
Rogue Playwright MCP - browser automation for agents
NOASSERTION -
autonomogithub.com/gtfodevs/autonomoupdated this year
Tired of 'it works' lies? Autonomo MCP makes your AI prove it—on real hardware, right in your editor.
NOASSERTION ★ 36 -
@iflow-mcp/debugbase-glancegithub.com/debugbase/glanceupdated this year
AI-powered browser automation MCP server for Claude Code
npm MIT -
A browser for LLMs, not humans.
Apache-2.0 ★ 17 -
qaclawgithub.com/vlddlv/qaclawupdated this year
Autonomous QA agent - runs browser-based tests via MCP
npm MIT -
Playwright browser automation for AI agents — screenshots, GIF/MP4/WebP recording, JSON feedback sidecar, MCP server.
pypi MIT -
myceliumgithub.com/yoda-digital/myceliumupdated this year
End-to-end encrypted messaging between Claude Code instances. Curve25519 PFS, Ed25519 TOFU, replay protection.
MIT -
Your AI agent implements the code. Canary Lab proves it works.
npm MIT ★ 4 -
✉️ Unofficial, pure-Rust Proton Mail client — library, CLI, and MCP server with end-to-end OpenPGP encryption.
MIT ★ 5 -
Ayme's MCP server for coding agents, and the page client it pairs with.
npm FSL-1.1-ALv2 -
Let coding agents verify UI changes on real iOS, Android, and web surfaces, then enforce reviewed proof in deterministic CI.
npm MIT -
AI-driven Android & iOS app testing over MCP: explore from a prompt, verify checkpoints, keep the evidence.
-
vwaygithub.com/chpr8/vwayactive
A virtual Wayland compositor an agent can use to test your desktop apps via MCP.
Apache-2.0 ★ 1 -
MCP server for xete — encrypted agent-to-agent messaging on Solana. Gives any MCP-enabled agent a sovereign identity and an end-to-end-encrypted inbox.
pypi MIT -
claude-playwrightgithub.com/smartlabsat/claude-playwrightupdated this year
Seamless integration between Claude Code and Playwright MCP for efficient browser automation and testing
npm MIT -
Browser automation driven by JSON or Markdown scenarios: projects, JS steps, test reports, local portal, optional AI generate and selector heal.
MIT ★ 1 -
Witness — browser acceptance checks for agent-built web apps. CLI, MCP, AI-drafted checklists, visual regression, and multi-browser reports.
npm MIT -
Mockzilla is the Next Gen Mocking Tool API Server to easier create endpoints faster for MVPs with AI and MCP Tooling
MIT ★ 8 -
MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland — virtual testing and live desktop automation
pypi MIT -
Tapline host: lets AI agents see and drive your own React Native / Expo app on a test phone on the same Wi-Fi (MCP server and CLI).
npm MIT -
MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland — 29 tools for virtual and live sessions
MIT ★ 80