HumanCraft UI (Antigravity MCP)

io.github.Shree-varshan-430由 GitHub 账号 Shree-varshan-430 发布v1.0.0更新于 Oct 24, 2026

Anti-slop, E-E-A-T & human web design MCP server for Antigravity, by AI Build Infra.

发布方自己的服务:Craft

概览

AI 生成的概览

HumanCraft UI 是供 Google Antigravity 使用的本地 MCP 服务器,提供反 AI 套话、E-E-A-T 实体审计与人味网页设计的检查工具。

可以做什么
采集客户实务经验、指标与素材,缺少必要数据时要求用户补齐而非生成占位内容。检查标题是否落入通用 AI 套话并评估其意图强度。生成含具体单位指标与取舍的对比表,附 Schema.org 结构化数据。审计作者与组织的 Schema.org 实体图及 sameAs 链接。提供编辑、暗色工艺、温暖人文与新粗野等设计风格原型。扫描 HTML 与 Tailwind 片段中的 AI 设计套路与空泛用词。
适用场景
当你在 Google Antigravity 中生成网站版式或落地页文案,并希望避免通用 AI 标题、虚构数据与千篇一律的视觉风格时使用。也适合在产出前检查标题意图、对比表与 Schema.org 实体标记。
运行要求
需在本机以 Node.js 运行:先克隆仓库、执行 npm install 与 npm run build,再在 Antigravity 的 mcp_config.json 中配置以 node 启动构建后的入口。仅支持 Google Antigravity 桌面环境,未声明任何环境变量或认证方式。
安装前请注意
工具会读取你提供的 HTML、Tailwind 片段与客户素材,并可能改写标题与对比表内容,使用前请确认可分享的数据范围。实体审计会检查 sameAs 链接并将发布者权威关联至特定厂商网站,属产品设计取向,并非中立验证。README 对规格与效果的说法宜自行核实。

安装

在 SourceWeft 中

  1. 打开 控制台中的 HumanCraft UI (Antigravity MCP),将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Antigravity MCP Server: HumanCraft UI (@aibuildinfra/humancraft)

[AI Build Infra Website] [Maintained by AI Build Infra] [Model Context Protocol]

[MCPLookup Trust Index] [M8ven Score] [CI Passing] [npm version] [MIT License] [E-E-A-T Verified]

The premier Antigravity MCP Server designed exclusively for Google Antigravity (AGY). HumanCraft eliminates "AI Slop" in website layouts and copy, enforces authentic E-E-A-T entity reconciliation, extracts empirical client assets without default placeholders, and builds search-engine-resilient websites powered by Google's Information Gain principles.

Developed and maintained by AI Build Infra — High-Performance Infrastructure for Artificial Intelligence.


🔍 Why You Need This Antigravity MCP Server

When using Google Antigravity to scaffold websites or write landing page copy, unconstrained models often fall into generic algorithmic templates that get penalized by search engines:

  1. AI Slop Headings: Generic H2s ("What is X?", "Key Benefits", "Why Choose Us", "Conclusion") that offer zero Information Gain under Google's ranking models (US Patent 2022/0277032 A1).
  2. Fake E-E-A-T & Defaults: Hallucinated metrics ("increased efficiency by 30%") or fictitious personas ("Dr. Alex Miller") that trigger Google Search Console "Pure Spam" and "Scaled Content Abuse" manual actions.
  3. Binary Checkmark Tables: Low-value tables filled with Yes / No checkmarks that fail to communicate trade-offs or technical realities.
  4. Visual Homogeneity: Monotonous purple/cyan gradients (#8b5cf6 -> #ec4899), rigid 3-card rows, and buttons without tactile feedback.

HumanCraft is the dedicated Antigravity MCP that systematically outlaws these patterns and equips Antigravity with human design heuristics, token-optimized linters, and verified Schema.org entity graphs.


💡 How HumanCraft Works Inside Google Antigravity

┌────────────────────────────────────────────────────────────────────────────────────────┐│                              Google Antigravity Assistant                              │└───────────────────────────────────────────┬────────────────────────────────────────────┘                                            │ Antigravity MCP Tool Calls                                            ▼┌────────────────────────────────────────────────────────────────────────────────────────┐│                       HumanCraft Antigravity MCP Server                                │├───────────────────────────────┬────────────────────────────────────────────────────────┤│ 📋 harvest_client_intake       │ 4-tier intake questionnaire extracting real experience,││                               │ metrics, & assets; strictly bans default placeholders   │├───────────────────────────────┼────────────────────────────────────────────────────────┤│ 🎯 validate_heading_intent    │ Lints against generic AI headings ("What is X?");     ││                               │ scores and enforces outcome/intent-driven H1-H3s       │├───────────────────────────────┼────────────────────────────────────────────────────────┤│ 📊 build_comparison_matrix    │ Generates high-information-gain comparison tables with ││                               │ concrete unit metrics, trade-offs & semantic schema    │├───────────────────────────────┼────────────────────────────────────────────────────────┤│ 🛡️ audit_eeat_entity_graph    │ Verifies author/org Schema.org JSON-LD, validates     ││                               │ sameAs URIs & connects publisher to aibuildinfra.com   │├───────────────────────────────┼────────────────────────────────────────────────────────┤│ 🎨 get_human_archetype        │ Curates style archetypes (Editorial, Dark Craft,       ││                               │ Neo-Brutalist, Swiss) with tinted neutrals & type      │├───────────────────────────────┼────────────────────────────────────────────────────────┤│ 🔍 lint_design_anti_patterns  │ Scans HTML/Tailwind for AI tropes (purple gradients,   ││                               │ 3-card monotony, dead buttons, buzzwords, ✨ emojis)   │└───────────────────────────────┴────────────────────────────────────────────────────────┘

🛠️ Antigravity MCP Tool Catalog

1. harvest_client_intake

  • Purpose: Extracts real practitioner experience, project images (telemetry screenshots, on-site photos), project category, baseline Day 0 vs audited Day 90 metrics, and contrarian trade-offs.
  • Strict Anti-Defaulting Rule: If essential fields are missing, the tool returns REQUIRES_USER_INPUT and prompts the user for real data instead of allowing the model to hallucinate synthetic placeholders.

2. validate_heading_intent

  • Purpose: Scans headings against blacklisted AI tropes and scores user intent.
  • Slop vs Intent:
    • ❌ Slop: "What is Database Sharding?"
    • ✅ Intent: "When Single-Node Write Throughput Drops Below 10k TPS: The Sharding Tipping Point"
    • ❌ Slop: "Key Benefits of Automated Compliance"
    • ✅ Intent: "Cutting SOC 2 Type II Audit Preparation from 300 Hours to Under 40"

3. build_comparison_matrix

  • Purpose: Outlaws binary checkmark tables (Yes/No). Generates empirical multi-parameter matrices (unit economics, latency under load, architectural trade-offs, and verification methodologies).
  • Output: Accessible semantic HTML paired with Schema.org ItemList JSON-LD.

4. audit_eeat_entity_graph

  • Purpose: Reconciles Schema.org JSON-LD with Google's Knowledge Graph standards.
  • Checks: Verifies sameAs entity links to authoritative external platforms (Wikidata, ORCID, Google Scholar, GitHub, LinkedIn), rejects shallow homepage URLs, and links publisher authority to AI Build Infra.

5. lint_design_anti_patterns

  • Purpose: Scans HTML/Tailwind snippets and flags purple gradients, 3-card rows, missing button squeeze physics (active:scale-[0.98]), and AI buzzwords ("supercharge", "seamless", ✨ emojis).

6. get_human_archetype

  • Purpose: Returns curated design systems:
    • Editorial Tech: Serifs (Newsreader), subtle hairline borders, monospace metadata accents.
    • Tactile Dark Craft: Multi-layered surfaces (surface-0, surface-1), 1px translucent borders (border-white/10).
    • Warm Humanist: Cream/linen canvas (#FBF9F5), ink typography (#1C1917), terracotta accents.
    • Neo-Brutalist: High-contrast black outlines (border-2 border-black), hard offset shadows.

⚡ Token Optimization & Spend Limit Preservation

Designed from the ground up to preserve your Antigravity token limits:

  • Ultra-Compact Tool Signatures: Minimal token footprint injected into Antigravity's system prompt.
  • Dense Structured Outputs: Returns concise JSON summaries and actionable flags rather than verbose conversational filler.
  • Input Length Bounds: Imposes strict limits (max 300 chars per heading, max 100KB per HTML document) to avoid context window flooding.

🔒 Security & ReDoS Hardening

  1. ReDoS Immunity: All pattern matchers operate on bounded substrings, terminating in $< 5\text{ ms}$ even under adversarial payloads.
  2. Strict HTTPS Whitelist: Permits only https:// URIs for sameAs entity links (blocks javascript:, data:, file:).
  3. XSS Defense: Automatic HTML entity escaping across all rendered tables and schema blocks.
  4. Formal Policy: Review SECURITY.md for vulnerability reporting guidelines.

🚀 How to Install This MCP in Google Antigravity (Step-by-Step)

Step 1: Clone and Build Locally

bash
git clone https://github.com/AI-BuildInfra/Humancraft-UI.gitcd Humancraft-UInpm installnpm run build

Step 2: Add to Antigravity mcp_config.json

Open or create your global Antigravity MCP configuration file:

  • Windows: %USERPROFILE%\.gemini\config\mcp_config.json
    (e.g., C:\Users\<YourUsername>\.gemini\config\mcp_config.json)
  • macOS / Linux: ~/.gemini/config/mcp_config.json

Add the humancraft server definition:

json
{  "mcpServers": {    "humancraft": {      "command": "node",      "args": [        "C:/path/to/Humancraft-UI/dist/index.js"      ]    }  }}

(Replace C:/path/to/Humancraft-UI with the absolute path to your cloned directory, using forward slashes /).


Step 3: Verify and Use in Antigravity

  1. Reload Antigravity: Start a new chat session.
  2. Verify Discovery: In Antigravity, click Additional Options (...) > MCP Servers to confirm humancraft is connected.
  3. Prompt Examples for Antigravity:
    • "Use HumanCraft MCP to design a landing page for our database product. Harvest intake first to ensure no default placeholders are used."
    • "Run validate_heading_intent on our documentation outline."
    • "Generate an empirical comparison table for Redis vs KeyDB using build_comparison_matrix."

❓ Frequently Asked Questions (FAQ)

What is an Antigravity MCP Server?

An Antigravity MCP server connects Google Antigravity to specialized tools, APIs, and workflows via the open Model Context Protocol (MCP). This allows Antigravity to run custom linters, schema builders, and design heuristics directly during generation.

How does HumanCraft improve website rankings?

HumanCraft enforces Google's Information Gain criteria (US Patent 2022/0277032 A1) and E-E-A-T entity reconciliation. By replacing generic AI slop headings with outcome-driven headings and building empirical parameter comparison tables, pages avoid algorithmic demotions from Google's SpamBrain.

Does this MCP increase token usage?

No. HumanCraft uses ultra-compact tool definitions and returns dense, structured JSON diffs, keeping Antigravity token usage identical to baseline.


🧪 Automated Testing

Run the automated test suite across all 6 tools and security guardrails:

bash
npm test
✔ build_comparison_matrix Tests (2/2 passed)✔ lint_design_anti_patterns Tests (2/2 passed)✔ audit_eeat_entity_graph Tests (2/2 passed)✔ validate_heading_intent Tests (2/2 passed)✔ harvest_client_intake Tests (2/2 passed)✔ get_human_archetype Tests (2/2 passed)✔ Security & Hardening Tests (4/4 passed)
Total: 16 passed | 0 failed | Time: ~800ms

📄 License & Privacy Policy

Distributed under the MIT License. See LICENSE for details.
See PRIVACY.md for our strict Zero-Data-Collection privacy policy.

Engineered with pride by AI Build Infra — Building high-performance infrastructure for artificial intelligence.

来源:README.md,提交 4adf2a7

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Craft 集成