Spec Score MCP

Name: Spec Score MCP
Author: openpoem

作者：openpoem版本 2.0.2i★ –i在你的电脑上运行

注册名称io.github.openpoem/spec-score-mcp

安装

概览

作者提供的说明（英文原文）

Score your specs before feeding them to an LLM. MCP server with radar chart visualization.

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。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i非常新★ –

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。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 设计、图片与音频

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
注册中心没有列出需要填写的密钥。

你需要

npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

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 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "spec-score": {
      "command": "npx",
      "args": [
        "-y",
        "spec-score-mcp"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add spec-score -- npx -y spec-score-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": {
    "spec-score": {
      "command": "npx",
      "args": [
        "-y",
        "spec-score-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": {
    "spec-score": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "spec-score-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。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

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

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8日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 openpoem 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
– 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

与“设计、图片与音频”中的其他服务器比较i

星标数多于此分类中其他 2782 个服务器的 0%
发布到注册中心的时间比此分类中其他 2782 个服务器的 2% 更新
基础检查结果等于或优于此分类中其他 2782 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

Spec Score MCP 安全吗？

它在 1 项适用的基础检查中通过了 1 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–，最新版本（2.0.2）于8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 Node.js。

有什么可以替代它？

同一分类中有：Figma Context MCP, Claude Real Video, Figma MCP Server

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：↓ 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

Figma Context MCP

Give your coding agent access to your Figma data. Implement designs in any framework in one-shot.

作者：GLips广泛使用↓ 16.1万/周★ 1.6万5个月前更新

在你的电脑上运行

安装

Claude Real Video

Let any LLM watch a video locally — and search everything it has ever watched.

作者：HUANGCHIHHUNGLeo广泛使用↓ 1106/周★ 22842个月前更新

在你的电脑上运行

安装

Figma MCP Server

The Figma MCP server brings Figma design context directly into your AI workflow.

作者：figma正在增长★ 215213个月前更新

在云端运行✓ mcp.figma.com

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。

Spec Score MCP

Score your specs before Claude builds from them.

A balanced spec produces balanced code. An unbalanced spec produces creative fiction.

The problem

When your spec is detailed on some axes but vague on others, Claude doesn't ask for clarification — it fills in the blanks. The result compiles, the tests pass, but it's not what you meant.

This tool catches that before you start building. It scores your spec on 4 axes, tells you which one is weakest, and gives you a concrete tip to fix it.

4 axes

Axis	Question it answers
completeness	Can Claude understand the full scope of what to build?
clarity	Is there only one way to interpret this spec?
constraints	Does Claude know what NOT to build?
specificity	Are there concrete, testable details?

Each axis scores 0.0 to 1.0. The balance score measures how evenly the 4 axes are covered.

Balance matters more than individual scores. A spec scoring 0.50 on all 4 axes (balance: 0.97) will produce better output than one scoring 0.95 / 0.95 / 0.20 / 0.90 (balance: 0.58). Why? That one weak axis — constraints at 0.20 — is exactly where Claude will improvise. You described what to build in detail, but forgot to say what's out of scope. So Claude builds everything you asked for, plus features you didn't.

On the radar chart: an even diamond beats a sharp spike.

Verdicts

Verdict	What it means
SHIP IT	Spec is ready — Claude knows what to build and what not to
ALMOST	One axis needs a small fix before you start
DRAFT	Multiple axes need work, but the structure is there
VAGUE	Well-organized but too abstract to act on
UNBOUNDED	Clear goal but no boundaries — Claude will over-build
OVER-CONSTRAINED	Lots of rules but unclear what the actual goal is
SKETCH	Starting point — needs detail on most axes

Not SHIP IT yet? The tool tells you which axis is weakest and what to add. Fix that axis, re-score, repeat. Most specs reach SHIP IT in 2-3 rounds.

Install

git clone https://github.com/openpoem/spec-score-mcp.git

cd spec-score-mcp && npm install && npm run build claude mcp add spec-score -- node $(pwd)/dist/mcp.js

The 3 tools are now available in every Claude Code session.

Usage

Slash commands

Clone this repo to get the built-in slash commands:

/project:scan my-feature-spec.md

Reads the file, scores it, and writes a my-feature-spec.md.scored.md with scores, verdict, tip, and a radar chart.

/project:compare blueprint.md implementation.md

Scores both files and writes a compared.scored.md with side-by-side radar charts.

Direct tool use

The 3 MCP tools work in any Claude Code conversation:

Tool	What it does
`spec_score`	Scores a spec on 4 axes, returns balance score and verdict
`spec_visualize`	Generates an SVG radar chart from scores
`spec_compare`	Side-by-side comparison of two scored specs

Ask Claude: *"Score this spec"*, *"Show me the radar chart"*, or *"Compare these two specs"*.

Example: from UNBOUNDED to SHIP IT

This tool scoring its own spec — four rounds, each fixing the weakest axis:

Round 1: the idea

Build a spec scoring tool

UNBOUNDED  0.12  Tip: What does 'scoring' mean? What axes? What output?

One axis is high (clarity — the goal is clear), everything else is near zero. Claude would build... anything. A web app? A CLI? A VS Code extension? No way to know.

Round 2: add context

Build an MCP server that scores specs on 4 axes: completeness, clarity,

constraints, specificity. Each axis is 0.0-1.0. Returns a balance score and verdict.

ALMOST  0.67  Tip: What are the verdicts? What does the tool NOT do?

Now Claude knows what to build. But constraints are still weak — it might add auto-fixing, CI integration, a database.

Round 3: add boundaries

Three tools: spec_score, spec_visualize, spec_compare.

Non-goals: no auto-fixing, no CI integration, no storage.

SHIP IT  0.84  Tip: Add testable criteria — what balance maps to which verdict?

Crossed the threshold. Claude now knows what to build AND what not to build. Specificity is still the weakest axis.

Round 4: add testable details

Balance = 1 - sqrt(variance)/mean. SHIP IT > 0.75, ALMOST > 0.60,

plus pattern-based verdicts. Node.js, MCP SDK, stdio transport.

SHIP IT  0.95  Spec is ready for implementation.

Four rounds: 0.12 → 0.67 → 0.84 → 0.95. Each round fixed exactly one thing.

The math

Claude scores each axis (0.0 - 1.0)
Normalize the vector: v / ||v||
Balance: 1 - sqrt(variance) / mean
Verdict: balance threshold + axis pattern matching

The scoring intelligence comes from Claude, not from the algorithm. The algorithm only measures balance.

Project structure

src/

mcp.ts # MCP server (3 tools) score.ts # Scoring engine visualize.ts # SVG radar charts .claude/ commands/ scan.md # /project:scan command compare.md # /project:compare command

OpenPoem — spec-score-mcp

MIT License.

Spec Score MCP

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“设计、图片与音频”中的其他服务器比较i

常见问题

替代选择

Figma Context MCP

Claude Real Video

Figma MCP Server

作者的 README

Spec Score MCP

The problem

4 axes

Verdicts

Install

Usage

Slash commands

Direct tool use

Example: from UNBOUNDED to SHIP IT

Round 1: the idea

Round 2: add context

Round 3: add boundaries

Round 4: add testable details

The math

Project structure