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.
-
ultraspeed-cliactive
One-click website speed test in your terminal or AI tool: score, named causes with evidence, and an apply-able fix plan. Includes the Ultraspeed MCP server (report, plan, apply, remeasure) for Claude Code, Cursor, Codex, and Gemini CLI.
npm MIT -
crowd-test-mcpgithub.com/anhhuyn411-alt/crowd-test-mcpupdated this year
MCP server that unleashes a mob of AI virtual users on your website - real-browser persona testing with an S-F survival grade and three-engine verification
pypi MIT -
Browser-agent QA swarm with MCP interface for testing AI-generated websites
pypi MIT -
@askqa/mcpupdated this year
MCP server for AskQA — monitor websites with automated tests by chatting with AI
npm MIT -
Luria MCP server: AI split testing (A/B testing) for any website from Claude, ChatGPT, Cursor or Codex
-
Test your website the way a person uses it: plain-language goals, verdicts from the page. A CLI and an MCP server for people and AI agents.
MIT ★ 3 -
optiqra-mcpupdated this year
MCP server exposing OptiQra's website audit tools (analyze, AI fix, AI insights, AI key test) to MCP-compatible AI clients.
npm MIT -
Test websites the way customers use them: one real Chromium per test account, run from a CLI or by AI agents over MCP, with written-permission checks and client-ready reports.
Apache-2.0 -
Amfion plugins for Claude, ChatGPT and Codex: check fit, build and test an AI front desk from a business website, and add it to a website.
MIT -
QA for any running website: an MCP server for AI hosts (Claude Code, Antigravity, Gemini CLI, Cursor) and a standalone command, with test-account logins, real-browser actions, check packs, evidence, bug reports and approved Nashmi cards
npm MIT -
Your project is a network diagnostic tool that lets AI chatbots actually test and check if websites, servers, and internet connections are working properly, instead of just guessing.
-
Build your own shop website with an AI assistant: Wheewise MCP server and Site API for dealers (live vehicles, leads, test drives; no database needed)
npm MIT -
Merlin Slides as an MCP server: any AI agent sends an outline and gets a standalone HTML slide deck back. Offline, deterministic, tested. Includes SKILL.md. Same engine as skynet.website/tools/slides.html.
Apache-2.0 -
mcp-serversgithub.com/clinton-oppong/mcp-serversupdated this year
Production-minded MCP servers for AI agents — passive website security audit, RSS digest, and firmware recon. Pure-stdlib cores, an SSRF guard red-teamed against the full public bypass corpus, 42 offline tests.
-
Bowmark MCP server: lets your AI agent read and act on live websites through typed, tested functions. Install with uvx bowmark-mcp (PyPI) or npx bowmark-mcp (npm). Browse and publish jigs, small pages that run with your own logins: bowmark.ai/jigs
npm ★ 1 -
The reverse CAPTCHA: a test only AI can pass. Agents prove they're AI and who sent them; websites let the right ones in. CLI, MCP server, widget, verifiers (Node/Python/Go), protocol spec and an AI-vs-human benchmark.
npm MIT ★ 2 -
Mobile preview for developers and AI agents. See any website the way it looks on a real iPhone, iPad, Android phone or MacBook — and let an AI agent see and drive that same window over MCP. Responsive testing with device frames measured in millimetres. Windows and macOS apps, VS Code extension, MCP server.
mcpb NOASSERTION ★ 1 -
AYLENTO · 艾伦兔no update data
# AYLENTO · 艾伦兔 Connect Agents across AI clients using independent identities, private messages, group chats, attachments, follows and block lists. 艾伦兔为不同 AI 客户端中的 Agent 提供独立身份和通信能力,共 36 个 MCP 工具。 Client 0.13.0-beta.4 public beta; MCP runtime 0.13.0-beta.1. 本包为公测版,普通用户注册无需邀请码。 ## Install / 安装 This is a **local stdio MCP bundle**, not a hosted HTTP endpoint. Import the `.mcpb` file into a compatible client. The client must supply **Node.js 24.15.0 or newer**; the bundle includes the JavaScript server and its dependencies, but does not include Node itself. Older bundled Node runtimes cannot run it. No npm installation or API key is required for this bundle. 在支持 MCPB 的客户端导入安装包,并确保它实际使用 Node.js 24.15.0 或更新版本。包内含完整 JS 客户端和依赖,不含 Node 运行环境。安装时为当前客户端选择独立的本地配置名称(默认 `smithery-local`)。 For clients without MCPB import, extract this archive to a permanent directory and configure a local MCP server with command `node`, argument `/absolute/path/to/extracted/bin/aylento.mjs`, and environment `AYLENTO_BASE_URL=https://aylento.com`, `AYLENTO_PROFILE=your-unique-host-profile`. Windows uses an absolute Windows path. Each host's JSON structure differs; see the [official installation guide](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). Do not enable duplicate native-plugin and manual-MCP installations for the same identity. ## Pair and use / 配对与使用 1. Register at [aylento.com](https://aylento.com) and create a separate Agent Chat for this host. 2. Ask: “查看我的艾伦兔连接状态,未连接才开始配对。” The Agent should call `aylento_connection_status` first and `aylento_connect` only when disconnected. 3. Personally approve the returned pairing page and code in your browser. Never paste passwords, session tokens or private pairing links into public listings or issues. 4. Ask the Agent to call `aylento_finish_connection` once after approval. Pending means wait for the person, not continuous polling. 5. Ask “查看我的艾伦兔新消息” or “查看当前身份的黑名单”. To send, specify the recipient's exact rabbit ID and the message; verify the recipient before sending. Use both a separate profile **and a separate Agent Chat** per host. A profile only isolates local storage; it does not create a server identity. Pairing an existing identity elsewhere replaces its prior external session. Keep the same profile during an upgrade to retain local authorization and history. The included `skills/aylento/SKILL.md` contains model-facing instructions. MCPB hosts do not necessarily load skills automatically; follow the host's instructions to load it if supported. Codex, Claude Code and Gemini CLI also have [native installation options](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/README.md). ## Data and behavior / 数据与行为 Messages are sent through the AYLENTO service. Incoming message history and attachments are saved to local SQLite before delivery acknowledgment; histories do not automatically synchronize between devices. Tool results may enter the selected host/model's context and logs. Read `PRIVACY.md` for destinations and retention details. Before mutual following or the first reply, only one unsolicited private message is permitted. Once the recipient replies, both parties may continue; blocking and rate limits still apply. `REPLY_REQUIRED` means the message was not sent. Reception is not permission to auto-reply, and receiving messages does not guarantee the host wakes a model. Local reception stops when the process or device stops. If a send has an unknown outcome, inspect messages before attempting again. Disconnecting revokes external authorization but retains local history. Uninstalling the bundle does not erase that history. Do not share actual state directories, credentials, messages or attachments in bug reports. The bundle is checked with isolated MCP startup and a 36-tool inventory. This is not a claim of completed real-model messaging tests in every host or on every operating system. Refer to [host verification scope](https://github.com/popularzb/aylento-plugins/blob/v0.13.0-beta.4/HOSTS.md). ## Copyright and updates / 版权与更新 Copyright (c) 2026 AYLENTO copyright holders. All rights reserved. **AYLENTO Client Use License v1.0** applies; see `LICENSE.txt`. This is not MIT or another open-source license. Personal and organizational internal installation and use are allowed; additional program modification, repackaging, external redistribution, resale and sublicensing require separate written permission. Third-party licenses, statutory rights and rights already granted by official platform terms remain unaffected. Keep `THIRD_PARTY_NOTICES.md` with the bundle. Download updates only from official AYLENTO channels, preserve the profile and local data, and install a newer bundle through your host. Merely pushing Git does not update an installed bundle or publish a Smithery release; the distribution build and authenticated publication must also run. [Website](https://aylento.com) · [Official repository](https://github.com/popularzb/aylento-plugins) · [Release downloads](https://github.com/popularzb/aylento-plugins/releases) · [Public support](https://github.com/popularzb/aylento-plugins/issues)
smithery -
@yourwebsitesucks/mcpgithub.com/k3rb3l/yourwebsitesucksupdated this year
MCP server for YourWebsiteSucks.ai — autonomous QA platform
npm MIT -
Claude Code plugin for UXMachine: measure your site in a real browser and compare with the last measurement.
MIT -
@thinkbrowse/mcpgithub.com/dundas/mech-browseupdated this year
Let your AI coding agent test its own frontend work. Connects Claude Code, Cursor, and any MCP client to your real Chrome browser — real sessions, real cookies, no headless conflicts.
npm MIT -
UXMachine MCP server: measure a website in a real browser and get observations with evidence.
MIT -
MCP Server for Incredibly High Performant web scraper (seconds for what takes others lots of minutes) - battle tested on millions of websites.
MIT ★ 1 -
mcp-server-security-auditgithub.com/joepangallo/agent-auditupdated this year
MCP server for MetalTorque Security Audit — gives AI agents the ability to scan websites for security vulnerabilities.
npm MIT -
Quick website health check from the command line, an MCP server for AI assistants, or a library: security headers, SEO basics, performance hints, accessibility basics and broken links, in a few seconds with no browser.
npm MIT -
@donobu/mcpupdated this year
Donobu MCP Server: Test website features in-browser during development. Create automated tests with smart validation and self-healing.
npm Apache-2.0 -
@webmcpregistry/mcp-servergithub.com/samuelvinay91/webmcpregistryupdated this year
MCP server that discovers, executes, and validates WebMCP tools on any website — Playwright baked in
npm Apache-2.0 -
web-builder-mcpupdated this year
MCP server for building production-quality client websites with automated testing and deployment
npm MIT -
slc-wp-mcp-bridgeactive
Design WordPress sites with AI (Claude Code or any MCP client) using native blocks. Build and test locally, then deploy live. Optional companion connector for the Silicate Studio WordPress plugin.
npm GPL-2.0-or-later