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。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

Cornea, deterministic visual inspection

作者:AbduljabbarBXR版本 0.2.2i★ 1i在你的电脑上运行代码仓库 ↗
注册名称io.github.AbduljabbarBXR/cornea

安装方法

What it does

Deterministic visual inspection for AI agents. Overlap, overflow, contrast, quality.

  • Connects 在你的电脑上运行
  • Account or key No key needed
  • Category 其他

为什么排在这里

列表按使用分(满分 100)排序,由以下部分组成

热度4/80GitHub 星标或每周下载量:较大的计 60,较小的计 20
新鲜度7/1230 天内有发布或代码更新得满分
仍在响应0/8上次检查时云端端点有响应
使用分11/100

质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)

安装

选择你使用的 AI 应用,然后复制设置。

通过 3/3 项检查 · 在你的电脑上运行

第一步:你用哪个 AI?

选择你用的应用,步骤会显示在下方。

Claude 暂时无法连接 Cornea, deterministic visual inspection

开发者尚未在 MCP 注册表中填写安装方式

ChatGPT 暂时无法连接 Cornea, deterministic visual inspection

开发者尚未在 MCP 注册表中填写安装方式

你可以改用这些方式

B · 其他 类中能连接 ChatGPT 的其他服务器

从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的

Claude Code 暂时无法连接 Cornea, deterministic visual inspection

开发者尚未在 MCP 注册表中填写安装方式

Cursor 暂时无法连接 Cornea, deterministic visual inspection

开发者尚未在 MCP 注册表中填写安装方式

VS Code 暂时无法连接 Cornea, deterministic visual inspection

开发者尚未在 MCP 注册表中填写安装方式

其他支持 MCP 的应用(如 Windsurf、Zed、Gemini CLI)添加方式各不相同,请在应用列表中查看

查看所有支持 MCP 的应用 →

JSON 设置在下方“开发者专用”中

卡住了?问问正在用 Cornea, deterministic visual inspection 的人💬 讨论 →

一览

每周下载量i
不在 npm/PyPI 上
连接方式
在你的电脑上运行
最新版本i
0.2.2
分类i
其他
发布到注册中心i
2026年9月4日
代码最后更新i
2026年9月23日
作者
AbduljabbarBXR
软件包
cargo: cornea
注册状态
活跃

哪些应用可以使用它

依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。

在你的电脑上运行,适用于

GooseLM StudioMsty StudioCherry StudioVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

全部应用及其优缺点 →

它能做什么

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

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18日

  • ✓ 通过

    作者与仓库一致

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

  • ✓ 通过

    仍在维护

    代码最后更新于2个月前

  • ✓ 通过

    有许可证

    使用 MIT

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

已公开的漏洞(OSV.dev)

未检查:只能检查标明版本的 npm 和 PyPI 包

我们检查什么 → · JSON

作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/abduljabbarbxr-cornea.svg)](https://mcp.popnx.com/en/servers/abduljabbarbxr-cornea)

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

用户评价

还没有评价

登录后写评价

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 20575 个服务器的 86%
  • 发布到注册中心的时间比此分类中其他 20575 个服务器的 27% 更新
  • 基础检查结果等于或优于此分类中其他 20575 个服务器的 99%

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

Cornea, deterministic visual inspection 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?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于2个月前,最新版本(0.2.2)于2个月前进入注册中心。

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。你的电脑上还需要有 Rust。

有什么可以替代它?

同一分类中有:World Monitor, openstatus, Oh My Posh Validator, Strata, Jitsu

功能相近的其他选择

同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。

如何看卡片:↓ 每周下载量i★ 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

World Monitor

Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 100 tools.

作者:koala73广泛使用★ 9.1万前天更新

在云端运行✓ 服务方 · worldmonitor.app

openstatus

Manage monitors, status pages, incidents and maintenances in your openstatus workspace.

作者:openstatusHQ广泛使用★ 92742个月前更新

在云端运行✓ 服务方 · openstatus.dev

Strata

MCP server for progressive tool usage at any scale (see https://klavis.ai)

作者:Klavis-AI正在增长★ 582614个月前更新

在云端运行仓库已归档✓ klavis.ai

Jitsu

Manage Jitsu data pipelines: destinations, streams, connections, functions, live events.

作者:jitsucom广泛使用★ 51354个月前更新

在云端运行✓ 服务方 · jitsu.com
与相似项目对比
本项
Cornea, deterministic visual inspection
World MonitoropenstatusOh My Posh ValidatorStrataJitsu
运行位置需要安装在电脑上在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装在云端运行,无需安装
需要密钥否否否否否否
可在 Claude 中按 + 添加否否否否否否
基础检查3/34/44/44/41/44/4
许可证MITAGPL-3.0AGPL-3.0MITApache-2.0MIT
价格登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用登记中未列出费用

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。

Cornea

Deterministic visual inspection for AI agents. The eyes a coding agent never had.

Cornea gives a coding agent that builds web pages a real way to *see* them. As a token-cheap, deterministic structural model it can reason over exactly, instead of megabytes of screenshots and raw DOM dumped into context.

An agent doesn't need a *photo* of a page. It needs to know is my layout broken, and how. Cornea computes an abstract *visual geometry model* of every element (box, position, z-order, computed styles) and derives inspection conclusions. overlap, overflow, contrast, quality. Then exposes them as native tools on three surfaces: CLI, MCP, and HTTP API.

One promise holds everything together: same input → byte-identical output. No Chromium, no sub-pixel variance, no server. A single ~1.4 MB binary.


Quick start

# Build (Rust 1.98+, edition 2024)

cargo build --release

Inspect a file, the simplest way to use Cornea

./target/release/cornea tests/fixtures/sample-bugs.html 360

Requires only cargo. No browser, no Node, no system dependencies. Builds fine on a phone-class device.

Or install the `cornea` command from npm (no Rust toolchain needed):

npm install -g optrex   # provides the cornea command

cornea --help


Visual guide: what Cornea does

Take this page below. It looks fine as source. But it's hiding four layout bugs. Cornea finds every one.

<!-- tests/fixtures/sample-bugs.html (excerpt) -->

Card 1 Card 2 Card 3

Left overlap Right overlap ... Hard to read on white

Run it and Cornea reports the damage instantly:

$ ./target/release/cornea tests/fixtures/sample-bugs.html 360

{ "html_file": "tests/fixtures/sample-bugs.html", "viewport_w": 360.0, "element_count": 17, "est_tokens": 1068, // <-- entire page read for ~1k tokens "report": { "total_elements": 17, "visible_elements": 14, "overlaps": [ ... 7 collisions ... ], "overflows": [ ... 1 clipped ... ], "contrast": [ ... 2 AA failures ... ], "quality": { "score": 0.06, "label": "broken" } } }

Each finding is precise and actionable:

FindingDetail
Overlapsection.row ⇄ div.overlap-right, area 20000 px². The absolutely-positioned boxes cover the cards
Overflowdiv.overflow-bad: right edge 600 exceeds viewport 360 → clipped
Contrastblack on blue: ratio 2.44:1. Fails WCAG AA (needs 4.5)
Contrast#cccccc on white: ratio 1.61:1. Fails WCAG AA

That is the value: hundreds of tokens, not hundreds of kilobytes, and a deterministic answer the agent can act on and re-verify.


Visual guide: the three surfaces

Cornea is one engine, three doors. All three returns identical inspection JSON because they funnel through a single shared dispatch.

1. CLI. Inspect a file
cornea <file.html | http(s)://url> [viewport_width] [viewport_height] [--js]
$ cornea page.html 360

{ "html_file": "page.html", "viewport_w": 360.0, "element_count": 42, "json_bytes": 8124, "est_tokens": 2193, "report": { "total_elements": 42, "visible_elements": 38, "overlaps": [], "overflows": [], "contrast": [], "quality": { "score": 1.0, "label": "good" } } }

2. MCP. Native agent tools over stdio
cornea --serve

An agent calls layout.* tools directly; it passes the page source, or a live URL (see URL capture below), per call:

→ {"method":"tools/call","params":{"name":"layout.overlaps",

"arguments":{"html":" A ..." ,"width":360}}} ← {"id":1,"result":{"content":[{"text":"[{\"a_sel\":\"...div \u21c4 ...div\",\"area\":20000}]"}]}}

ToolReturns
layout.inspectFull visual model + report
layout.overlapsElements whose boxes collide
layout.overflowClipped / collapsed / off-screen
layout.contrastWCAG AA ratios for text elements
layout.quality0..1 health score + issue list
layout.fidelityWhich CSS features are exact vs approximated
3. HTTP API. Call from anything
cornea --serve-http [addr]        # default 127.0.0.1:8080
curl -s -X POST http://127.0.0.1:8080/inspect \

-H 'Content-Type: application/json' \ -d '{"html":" bady ","width":360}'

{"total_elements":1,"contrast":[{"selector":"...>p","fg":"#cccccc","bg":"#ffffff",

"ratio":1.61,"pass_aa":false}]}

RouteMethodReturns
/inspectPOSTFull report
/overlapsPOSTCollisions
/overflowPOSTClipped / collapsed / off-screen
/contrastPOSTWCAG ratios
/qualityPOSTHealth score
/fidelityGETEngine capabilities
/healthGETLiveness

Watching a live page (URL capture)

Every surface accepts a URL where the HTML would go. Cornea fetches the page, inlines its external stylesheets and external scripts (relative URLs resolved against the page), then inspects what a browser would actually show. That is the live coding session loop: run your dev server, point cornea at it, read the layout verdict.

cornea http://localhost:3000 390
{ "url": "http://localhost:3000", "width": 390, "height": 844 }  // HTTP /inspect
{ "method": "tools/call", "params": { "name": "layout.quality",

"arguments": { "url": "http://localhost:3000", "width": 390 } } } // MCP

Honesty around capture:

  • Failed fetches leave the original tag in place and record a note, so the report warnings still flag what did not load.
  • A positive height emulates a fixed viewport (screenshot frame, iframe, email) and enables below the fold clipping checks. Default 0 means an unbounded scrolling page.
  • Capture is a snapshot in time. Determinism holds engine side: the same fetched bytes always produce the same report.
  • Plain HTTP is supported natively. HTTPS pages need a TLS stack, which the binary does not carry; capture from a local http dev server or pre inline the page with a fetch layer of your own.

Architecture

                    ┌─────────────────────────────────────┐

HTML + CSS ──► │ cornea (one binary) │ │ │ │ dom.rs html5ever ──► tree │ │ css.rs + inline │ │ │ │ layout.rs deterministic layout │ │ (block/inline/flex, │ │ box model, z-index) │ │ │ │ │ model.rs Visual Geometry Model │ │ │ │ │ inspect.rs overlap / overflow / │ │ contrast / quality │ │ │ │ │ rest.rs canonical dispatch │ └───────┬─────────────┬───────────────┘ │ │ ┌─────┴────┐ ┌────┴───────────────┐ │ CLI │ │ MCP (stdio) / HTTP│ │ cornea │ │ layout.* / REST │ └──────────┘ └────────────────────┘

Read the full technical spec: CORNEA-ARCHITECTURE.md


Fidelity. Honest about what's approximate

Cornea never silently fakes precision. layout.fidelity tells an agent exactly what it can trust, and every report carries its own warnings for sources the engine saw but did not apply (external stylesheets, external scripts, media queries, unresolved colors):

{

"exact": ["box model", "block flow", "inline text estimates", "flex row/column (no wrap)", "z-index", "visibility", "absolute/fixed left/top", "inline styles", "class/id/tag selectors", "WCAG contrast (hex, rgb, hsl, alpha)"], "approximate": ["text glyph width (not shaping)", "flex-grow/flex-basis distribution", "percentage widths", "overlap semantics ignore intentional stacking"], "deferred": ["grid (parsed as block flow)", "media queries", "border-radius", "external stylesheet when not captured", "complex selectors (combinators, pseudo)"], "js": { "engine": "boa", "phase": "A", "enabled": "opt-in via --js / js:true", "dom_shim": "static HTML mirrored in first; getElementById; innerHTML parses markup", "unsupported": ["async APIs", "event dispatch", "selector engine", "React/SPA mounting (Phase B)"] } }

JavaScript built-in pages (Phase A)

Cornea can execute inline ` ` that builds its DOM via a minimal shim, then run the result through the same deterministic layout engine:

cornea page.html 360 --js            # inline scripts build the DOM first
{ "html": "<p>…</p>", "width": 360, "js": true }   // HTTP /inspect and MCP layout.*
  • Static HTML is mirrored into the shim before scripts run, so scripts can attach to existing nodes via document.getElementById, and innerHTML parses real markup into elements. Static content survives script runs.
  • style.* assignments are serialized back to style="…" and participate in overlap/contrast checks.
  • Async APIs are rejected (setTimeout, fetch, …) rather than hung. Any such use is surfaced in the report's js_notes, so determinism stays a guarantee.
  • External runs only when a capture layer (URL capture) inlined its body first.
  • Full React/SPA mounting is Phase B (experimental). Tracked in ROADMAP-JS.md.

Visual guide: testing (battle-tested)

54 tests run clean with cargo test; CI enforces fmt, clippy `-D warnings`, release build, tests, and a CLI smoke test on every push.

$ cargo test

Running unittests src/lib.rs ... 36 passed // determinism, overlap, overflow, Running unittests src/main.rs ... 9 passed // contrast, inline flow, flex, Running tests/endpoints.rs ... 9 passed // nesting, empty input, MCP, CLI, JS, capture

  • Determinism. Same page inspected twice gives byte-identical JSON (the core thesis).
  • Bug detection. The fixture's overlaps, overflows, and contrast failures are all asserted.
  • End-to-end. The compiled binary is spawned and layout.* is called over real stdio MCP.
  • HTTP. The TCP server boots on an ephemeral port and real requests are made.
  • Live capture. A real page is served over a local socket; linked CSS must change a contrast verdict.
  • Edge cases. Empty HTML, deep nesting (no crash), display:none, long text, flex row/col, inline wrapping.

Layout support (v1 scope)

FeatureStatus
Block flow, box model (content/border-box)exact
Inline text runs (horizontal, wrapping)exact
Flex row / column (simplified, no wrap)approximate
Absolute / fixed positioning (left/top)exact
z-index, visibility, display:noneexact
.class / #id / tag selectors + inline stylesexact

| WCAG contrast (hex, rgb, hsl, al

只显示了开头部分;其余内容请在仓库中阅读