Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Visual testing for coding agents: your agent sees every UI change it makes and triages each diff.
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。
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。
选择你使用的 AI 应用,然后复制设置。
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:
https://uiverify.ai/mcp在终端中运行这条命令
claude mcp add --transport http uiverify https://uiverify.ai/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"uiverify": {
"url": "https://uiverify.ai/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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"uiverify": {
"type": "http",
"url": "https://uiverify.ai/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:
https://uiverify.ai/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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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
发布者(igrlk)不是仓库所有者(uiverify);可能是其他人代为上架的
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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。
它在 1 项适用的基础检查中通过了 0 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。
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。
GitHub 仓库最后更新于–,最新版本(1.2.0)于10天前进入注册中心。
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。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Apify MCP Server
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
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡
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。
Catch unintended UI changes on every pull request. UI Verify renders your components in the cloud, diffs them against a baseline, and lets a coding agent triage what actually changed.
uiverify.ai · GitHub · CLI · Playwright SDK · Vitest SDK · Bun SDK · Skills
UI Verify is a hosted visual-testing service that plugs into your CI. On each PR it:
bun test with the Bun SDK, or from finished screenshots your own harness already produces (native, mobile, React Native) uploaded straight for diffing.This repository holds the open-source client packages, everything that runs in *your* repo. All rendering, diffing, and judging happens server-side; these packages only build a bundle, upload it over HTTP, and read back status, so each is safe to read, fork, and self-host against.
# 1. Install the CLI in your project
npm i -D uiverify
export UIVERIFY_API_KEY=... # from uiverify.ai
npm run build-storybook npx uiverify upload --static-dir storybook-static
Already have screenshots? If your harness already produces them (Detox, Maestro, native snapshot tests, anything), upload the PNGs directly, no Storybook and no rendering required. UI Verify diffs, judges, and baselines them just the same:
npx uiverify upload --screenshots ./screenshots
This is how native, mobile, and React Native projects use UI Verify: each image is keyed by its path under the directory, so a screen maps to the same baseline every build, and you can upload only the screens you changed and carry the rest forward.
Prefer to drive it from your agent? Install the skills (below) and run /uiverify:setup-visual-testing. It detects your capture path, wires CI, and writes the first stories for you.
uiverify checkWhile an agent is editing, it can render just the stories it is touching and diff them against the real CI baseline on the fleet - a "would this pass" answer without waiting for CI:
npm run build-storybook
npx uiverify check --target 'components-button--*' --static-dir storybook-static
It renders only the stories you name (repeatable --target, globs or exact ids), posts no PR check, and never moves a CI baseline. A changed result is informational (exit 0) - review the pixels over the UI Verify MCP (get_build / render_diff_image) and accept in the dashboard or with accept_build to set a branch-scoped preview baseline, so your own accepted changes stop re-flagging on the next check. CI stays the only path to a main baseline.
| Package | Install | What it does |
|---|---|---|
| [`uiverify`](packages/cli) | npm i -D uiverify | The CLI. uiverify upload is the CI uploader (Storybook bundle, Playwright/Vitest/Bun archive, or a directory of finished screenshots) - streams render progress and reflects the visual verdict in its exit code. uiverify check is the agent edit-loop check - renders just the stories you name against the real CI baseline, without posting a check or moving a baseline. |
| [`@uiverify/playwright`](packages/playwright) | npm i -D @uiverify/playwright | The Playwright capture SDK. Swap @playwright/test for it and each test archives its final UI state (serialized DOM + resource bytes) for UI Verify to replay and diff. |
| [`@uiverify/vitest`](packages/vitest) | npm i -D @uiverify/vitest | The Vitest capture SDK. Add uiverifyPlugin() to your Vitest config and each browser-mode test archives its final DOM (serialized DOM + resource bytes) for UI Verify to replay and diff; takeSnapshot() takes named snapshots instead. |
| [`@uiverify/bun`](packages/bun) | bun add -d @uiverify/bun | The Bun capture SDK. Write visual tests on bun test that drive your installed Chrome, and each test archives its final page (serialized DOM + resource bytes) for UI Verify to replay and diff; run() starts your app and runs the test files. |
| [`@uiverify/skills`](packages/skills) | npx skills add, see below | Agent skills: SKILL.md workflows a coding agent runs in your repo to set up visual testing, author economical + deterministic stories, and triage builds. As a Claude Code or Cursor plugin, or a Gemini CLI extension, it also connects the UI Verify MCP server. |
| [`@uiverify/workflow-skills`](packages/workflow-skills) | Claude Code plugin, see below | The agentic-development loop we build UI Verify with: factory, design, review-loop, e2e-verify, babysit-pr, and the skills that tune it. |
Install the skills into any coding agent with one command (skills.sh):
npx skills add uiverify/uiverify
Works in Claude Code, Cursor, Codex, Copilot, Gemini, and any agent that reads a skills folder. Add --list to pick individual skills, and run npx skills update to pull the latest.
Or, on Claude Code, install as a plugin so updates arrive automatically:
/plugin marketplace add uiverify/uiverify
/plugin install uiverify@uiverify
Either way, invoke them by name: /uiverify:setup-visual-testing, /uiverify:triage-visual-changes, and more. See packages/skills for the full list and a copy-in-by-hand alternative.
On Gemini CLI, install the same skills plus the MCP server as an extension, then log in once:
gemini extensions install https://github.com/uiverify/uiverify
In a Gemini CLI session, run /mcp auth uiverify and log in to UI Verify in your browser.
The agentic-development loop we build UI Verify with (factory, design, review-loop, e2e-verify, babysit-pr) is a second plugin in the same marketplace: /plugin install uiverify-workflow@uiverify, then /uiverify-workflow:factory. See packages/workflow-skills.
Connect the UI Verify MCP server and your coding agent (Claude Code, Cursor, Codex, and others) can pull a pull request's UI changes into the conversation, look at each diff, read the AI judge's verdict, and accept the intended baselines - without leaving the terminal.
claude mcp add --scope project --transport http uiverify https://uiverify.ai/mcp
If you installed the plugin above, it already connects this server, so skip the command and just log in from /mcp. Otherwise restart Claude Code after adding it, run /mcp, pick uiverify, and log in to UI Verify in your browser. You log in once and the connection reaches every project in every team you are a member of. --scope project writes it to your committed .mcp.json so the whole team gets it; the file holds no secret, since each teammate logs in with their own account. In Cursor, add { "mcpServers": { "uiverify": { "url": "https://uiverify.ai/mcp" } } } to .cursor/mcp.json and log in from its MCP settings. In Gemini CLI, the extension above connects it, and /mcp auth uiverify logs you in. Full guide: Triage visual changes from your coding agent.
The server is remote (streamable HTTP) - there is nothing to install or run. It exposes:
| Tool | What it does |
|---|---|
list_projects | List the projects you can access, with the projectId to pass when you have several |
list_builds | List recent UI Verify builds |
get_build | Get what changed in a build |
list_build_stories | Page through a build's stories by status |
get_pr_changeset | Get what a PR does to the UI vs its base branch |
list_pr_stories | Page through the PR-vs-base changeset by kind |
get_diff | Per-story diff detail with image URLs |
render_diff_image | Fetch the actual pixels of a story image |
review_diff | Accept, deny, or ignore one story's change |
accept_build | Accept every changed story in a build |
Complete, runnable projects under examples/ — one per capture path. Copy a folder, add a project API key, and it works.
| Example | Capture path |
|---|---|
| [`examples/storybook`](examples/storybook) | Storybook stories (no SDK, upload --static-dir) |
| [`examples/vitest`](examples/vitest) | Vitest browser-mode tests with @uiverify/vitest |
| [`examples/playwright`](examples/playwright) | Playwright end-to-end tests with @uiverify/playwright |
| [`examples/bun`](examples/bun) | Bun visual tests (bun test) with @uiverify/bun |
| [`examples/react-native`](examples/react-native) | Finished screenshots (native / mobile / React Native) with upload --screenshots |
The first four capture a slice of the same Shoppy storefront; the React Native one is a small Expo app driven by Maestro. Each folder has its own CI workflow.
pnpm install
pnpm -r build # CLI builds dist/uiverify.js, playwright builds dist/ pnpm -r test pnpm -r typecheck
The CLI requires UIVERIFY_API_KEY and talks to https://uiverify.ai by default (override with --api-url / UIVERIFY_API_URL for self-host or local dev). See each package's README and DEVELOPMENT.md for internals.
MIT © UI Verify