原型 · 预览版：收录官方注册中心里的全部服务器，每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚
新手模式 开
配色跟随系统浅色深色
语言ไทยEnglish中文日本語한국어EspañolDeutsch
☰ 菜单设置
新手模式 开
配色跟随系统浅色深色
语言ไทยEnglish中文日本語한국어EspañolDeutsch

Kilotest

作者：jrpool版本 63.2.0i★ –i在云端运行
注册名称io.github.jrpool/kilotest

安装

概览

作者提供的说明（英文原文）

Ensemble testing of web pages for accessibility, usability, and web standards

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

你需要

你用的是哪个应用？

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude：

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址，然后点击 Add
  4. 如果要求登录，请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://kilotest.com/mcp

在终端中运行这条命令

claude mcp add --transport http kilotest https://kilotest.com/mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "kilotest": {
      "url": "https://kilotest.com/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "kilotest": {
      "type": "http",
      "url": "https://kilotest.com/mcp"
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

ChatGPT 只能连接互联网上的服务器：

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add（部分套餐需要先在 Advanced 中开启 Developer mode）
  3. 粘贴下面的地址，起个名字，然后保存
  4. 如果要求登录，请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://kilotest.com/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上，无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

工具名称和描述与服务器在 2026年11月6日 报告的完全一致。这些内容由作者撰写，不是我们写的；我们以纯文本形式显示。

  • getKilotestOverview

    Explains what Kilotest is, what its tools do, and how its results are structured. Use this before any other tool when the available tools or workflow are unclear. Returns a prose overview of the Kilotest domain, the tool workflow, and links to further documentation. Kilotest inte

  • listPages

    Lists all pages Kilotest has tested. Use this first to discover whether a page already has any reports before requesting a test. Returns, for each tested page, its description, URL, and the identifier of its latest available report.

  • listIssues

    Lists the issues reported in one report, along with the history of all reports about the same page. Use this after listPages to switch to an earlier or later report or to begin examining this report. Returns the history and the basics about this report’s issues.

  • listViolators

    Lists the elements of a tested page that were reported as exhibiting one issue in one report. Use this after listIssues to drill down from an issue to the elements violating rules belonging to that issue. Returns basics about each violating element.

  • listDiagnoses

    Lists the diagnoses that rule engines gave for how one element exhibited one issue in one report. Use this after listViolators to get details about the element as a violator of the issue. Returns, for each rule engine that reported a violation by the element of a rule belonging t

  • getReport

    Retrieves one entire report as JSON, with all of its issues, violators, and diagnoses. Use this instead of drilling down through listIssues, listViolators, and listDiagnoses when the full report is needed in one call. Returns the complete report data for the specified report iden

  • requestNewTest

    Submits a request to test a page that has no report yet; queued for manager approval. Use orderNewTest instead for immediate, automatically approved testing. Returns a request confirmation with disposition details.

  • requestRetest

    Submits a request to retest a page whose existing report is considered obsolete; queued for manager approval. Use orderRetest instead for immediate, automatically approved retesting. Returns a request confirmation with disposition details.

  • requestFeature

    Submits a request to add a new feature or improve an existing one; queued for manager review. There is no immediate-approval alternative for feature requests. Returns a request confirmation with disposition details.

  • reportDisagreement

    Reports that you disagree with a diagnosis shown by the listDiagnoses tool; queued for manager review. Use this after listDiagnoses when you believe a rule violation was incorrectly diagnosed or classified into an issue, providing the engineID and ruleID shown in the diagnosis an

  • orderNewTest

    Orders testing of a page that has no report yet, with automated approval or rejection and immediate enqueueing if approved. Use this instead of requestNewTest when immediate testing is wanted; testing typically takes 2 to 4 minutes. Returns an order confirmation and disposition d

  • orderRetest

    Orders a retest of a page whose existing report is considered obsolete, with automated approval or rejection and immediate enqueuing if approved. Use this instead of requestRetest when immediate retesting is wanted; testing typically takes 2 to 4 minutes. Returns an order confirm

  • awaitTest

    Waits for a job ordered via the orderNewTest or orderRetest tool to finish, using the report identifier either tool returned. Use this instead of polling listIssues when an immediate answer is preferred. Blocks until the report is ready, the job fails, or a maximum wait time elap

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过 GitHub 账户 jrpool 验证，该账户拥有此仓库

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • ✓ 通过

    端点有响应

    在 1412 毫秒内响应（HTTP 200）

  • – 不适用

    使用 OAuth 登录

    无需登录

  • ✓ 通过

    工具描述中没有隐藏指令

    已读取 13 个工具描述，未发现针对 AI 的隐藏指令

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32509 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32509 个服务器的 97% 更新
  • 基础检查结果等于或优于此分类中其他 32509 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Kilotest 安全吗？

它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

注册中心没有列出必需的密钥，不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端？

它在作者的云端运行。通过互联网连接，无需安装，但你发送的内容会经过作者的服务器。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（63.2.0）于今天进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接，所以接受远程 MCP 服务器的应用也可以使用，例如开启开发者模式的 ChatGPT。

有什么可以替代它？

同一分类中有：Spec Driven Development, Remote Desktop Commander, Fomu MCP

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Spec Driven Development

作者：formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者：desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新
安装

Fomu MCP

作者：gabrielmahia

Kenya government form guides: checklists, draft letters, eCitizen, Huduma, timelines. Sample data.

在你的电脑上运行今天更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Kilotest

An ensemble testing and reporting service for front-end web quality

Features

This application uses an ensemble of 12 rule engines to test web pages for front-end quality (i.e. accessibility, usability, and web standards, including HTML, CSS, ARIA, and WCAG).

The testing paradigm employed by Kilotest is discussed in these papers:

Kilotest acts as a web server for human users, an MCP server (streamable HTTP, no authentication) for AI platforms, and an API for programmatic access.

Testing for Kilotest is performed by one or more workers (testing agents) that obtain jobs from Kilotest, perform them, and send reports of the results back to Kilotest. Those agents are instances of the Testaro package. Thus, the pages that Kilotest tests need not be on the public Internet. They need only be reachable by the Testaro workers that do the testing for Kilotest. So, one or more Testaro workers running inside a private intranet can test internal pages, as well as any external ones reachable from inside the intranet.

An active production instance of Kilotest may require multiple Testaro workers to handle the load, because testing one web page typically takes 2 to 4 minutes and workers test only one page at a time.

Getting started locally with 1 worker

Installation

In the steps below, hosts T and K may be the same host or two different hosts. Host T can be a Debian stable, Ubuntu LTS, Windows, or macOS host. Host K can be any server host that can run the latest LTS version of Node.js. If hosts T and K differ, then they must be open to https traffic and host K must permit https requests from host T.

  1. Clone the Testaro project into a new directory on host T.
  2. In that directory, install the Testaro dependencies: npm install.
  3. Update the Testaro dependencies and rebuild: npm run deps.
  4. Clone the Kilotest repository into a new directory on host K.
  5. In that directory, install the Kilotest dependencies: npm install.
  6. Copy the env.testaro file from the kilotest directory to .env in the testaro directory and replace the __placeholder__ values in .env with actual values.
  7. Copy the env.example file in the kilotest directory to a new .env file in the same directory and replace the __placeholder__ values in .env with actual values. TESTARO_WORKERS is a JSON object mapping each Testaro worker's ID to an object with its secret and its name; the ID and secret for a worker must match the NETWATCH_URL_WORKER_ID and NETWATCH_URL_AUTH values in that worker's .env. A worker authenticates each request with an HTTP Basic Authorization header (id:secret, base64-encoded); as of this writing that header is not yet sent by the published Testaro package, so this scheme requires a matching update to Testaro's netWatch.js request code (only to send the header; no change to Testaro's handling of jobs or reports is needed). The ID is a credential and is never published; the name is written by Kilotest into a job's and report's sources.worker property, which Testaro does not read or alter, so it is a distinct property from sources.agent (Testaro's own, untrusted, self-reported label, which Kilotest ignores). Choose a name that is safe to appear in every report Kilotest serves. ALLOW_INTERNAL_TARGETS controls whether this deployment can be induced to test pages at private, loopback, or link-local addresses; see SERVICE.md before changing it from its default.
Usage
  1. In the testaro directory, make Testaro start listening for jobs: node call netWatch true nn true, where nn is the number of seconds to wait between checks for new jobs. Note that Kilotest promises nearly immediate review and, on approval, immediate execution of “orders” for tests and retests, with typical total elapsed time 2 to 4 minutes. That promise implies a promise to keep nn small. A reasonable value is between 10 and 20.
  2. In the kilotest directory, start the Kilotest service: node index.
Contributing

Contributions are welcome! You can use GitHub issues to initiate discussions and propose changes. If you want to contribute code, please fork the repository and create a pull request.

Making Kilotest a service

See the SERVICE.md file for instructions on how to make Kilotest a service.

Using Kilotest as an AI tool

Kilotest is not only a web application but also an API and an MCP server. AI platforms and models can use Kilotest via those interfaces.

The public URL for models using the MCP server at kilotest.com is https://kilotest.com/mcp. The MCP server is registered at several registries. See AI-TOOLS.md for details.

There is additional documentation at:

Maintenance

These are the routine steps for maintaining Kilotest as currently deployed.

No API changes

When you make a change in a feature branch without any API or tool contract change:

  1. Stage, commit, and optionally push all changes.
  2. Execute npm run prePR -- (major, minor, or patch).
  3. Submit a pull request.
  4. When all checks succeed, squash-merge to main and delete the feature branch on GitHub.
  5. Execute npm run postPR (with interactive browser authentication).
  6. Wait until npmjs.com has processed the publication.
  7. Use git pull, npm ci, and pm2 restart kilotest (but not npm audit fix) to deploy the revised main branch on the public server.
API changes

When you make an API or tool contract change in a feature branch:

  1. lhm.plugin.json: Transform it to match api/schemas.ts and mcp.ts.
  2. llms.txt, llms-full.txt, capability.md, README.md: Update parameter and path names.
  3. Stage, commit, and optionally push all changes.
  4. Execute npm run prePR -- (major, minor, or patch).
  5. Submit a pull request.
  6. When all checks succeed, squash-merge to main.
  7. Execute npm run postPR (with interactive browser authentication).
  8. Wait until npmjs.com has processed the publication.
  9. Use git pull, npm ci, and pm2 restart kilotest (but not npm audit fix) to deploy the revised main branch on the public server.
  10. Visit the RapidAPI Studio and update the API definition at Hub Listing → Definitions → CI/CD → Import OpenAPI by uploading the regenerated openapi-3.0.yaml.
  11. Visit the Claude directory, edit any changed entries, and submit the changes.

If any step fails, see the details in docs/AI-TOOLS.md for troubleshooting instructions.

问 PopNx