Stylemcp

io.github.3DUNLMTD由 GitHub 帳號 3DUNLMTD 發布v0.1.4更新於 Oct 24, 2026

Brand rules for AI outputs. Validate and rewrite text to match your brand voice.

已驗證STDIO僅桌面效率與工作流開發者工具

概覽

AI 產生的概覽

依品牌風格包檢查並改寫 AI 產生的文字,讓助理能驗證文案、修正語氣並讀取品牌規則。

可以做什麼
  • 依品牌風格包驗證文字,回傳分數與違規項目
  • 依品牌語氣改寫文字
  • 讀取風格包背後的規則:語氣與語調指南、已核准的文案模式、CTA 規則與設計權杖
  • 列出可用的風格包(例如 saas、ecommerce、healthcare、finance)
適用情境
適合在助理撰寫行銷、產品或介面文案時,依既定品牌語氣逐則檢查或改寫;也適合讓模型在寫作過程中隨時查閱品牌規則。
執行需求
以 stdio 方式在使用者本機執行,通常透過 npx stylemcp 啟動,需要 Node.js。README 另說明了託管 REST API 以及以 Docker 或 npm 自架的方式,其中會用到 PORT、STYLEMCP_API_KEY 與 GITHUB_WEBHOOK_SECRET。MCP 伺服器本身未宣告任何憑證。
安裝前請注意
改寫工具會變更文字,發布前請人工複核。README 的託管 API 範例會把文字送到外部服務;若文案涉及機密,請改用本機伺服器。自架並啟用驗證時,需自行設定 STYLEMCP_API_KEY 與 GITHUB_WEBHOOK_SECRET。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Stylemcp,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

StyleMCP

Executable brand rules for AI models and agents. Keep every AI-generated message on-brand.

What is StyleMCP?

StyleMCP validates and rewrites AI-generated text to match your brand voice. Use it as:

  • REST API - Validate text from any application
  • MCP Server - Direct integration with Claude and other AI agents
  • CLI - Check copy in your terminal or CI/CD
  • GitHub Action - Catch off-brand copy in pull requests

Quick Start

API

bash
curl -X POST https://stylemcp.com/api/validate \  -H "Content-Type: application/json" \  -d '{"text": "Click here to learn more!"}'

Response:

json
{  "valid": false,  "score": 65,  "violations": [    {      "rule": "no-click-here",      "severity": "error",      "message": "Avoid 'click here' - describe the destination instead",      "suggestion": "Learn more about our features"    }  ]}

CLI

bash
# Installnpm install -g stylemcp
# Validate textstylemcp validate "Click here to learn more"
# Validate filestylemcp validate src/copy/homepage.json --pack saas
# Rewrite textstylemcp rewrite "Please utilize our product" --mode aggressive

MCP (Claude Desktop)

Add to your claude_desktop_config.json:

json
{  "mcpServers": {    "stylemcp": {      "command": "npx",      "args": ["stylemcp"]    }  }}

Now Claude can validate and rewrite text using your brand rules.

API Endpoints

MethodEndpointDescription
POST/api/validateValidate text against brand rules
POST/api/rewriteRewrite text to match brand voice
POST/api/validate/batchValidate multiple texts
GET/api/packsList available style packs
GET/api/packs/{pack}/voiceGet voice guidelines
GET/api/packs/{pack}/ctasGet CTA rules
GET/api/mcp/sseMCP SSE endpoint
POST/api/mcp/callMCP tool calls

Style Packs

StyleMCP uses style packs - YAML files that define your brand rules.

Available Packs

PackBest ForKey Features
saasB2B SaaS productsProfessional, clear, helpful tone
ecommerceDTC & retail brandsFriendly, conversion-focused, no pushy CTAs
healthcareMedical & wellnessCompliant language, no cure claims, person-first
financeFintech & bankingPrecise, risk-aware, no guaranteed returns

Example: saas Pack

  • Vocabulary: Prefer "use" over "utilize", "help" over "assist"
  • Forbidden words: "synergy", "leverage", "cutting-edge", "game-changing"
  • Patterns to avoid: "click here", "we're sorry for any inconvenience"
  • CTA rules: Avoid "Submit", "Click here", "OK" - prefer "Save", "Create", "Sign up"

Pack Structure

packs/  my-brand/    manifest.yaml      # Pack metadata    voice.yaml         # Tone, vocabulary, forbidden words    copy_patterns.yaml # Reusable copy templates    cta_rules.yaml     # Button/CTA guidelines    tokens.json        # Design tokens (optional)

Create Your Own Pack

bash
# Copy the default packcp -r packs/saas packs/my-brand
# Edit the rulesnano packs/my-brand/voice.yaml
# Use your packcurl -X POST https://stylemcp.com/api/validate \  -d '{"text": "Your text", "pack": "my-brand"}'

voice.yaml Example

yaml
tone:  summary: "Friendly, clear, and helpful"  attributes:    - name: friendly      weight: 0.8    - name: professional      weight: 0.7
vocabulary:  rules:    - preferred: "use"      avoid: ["utilize", "leverage"]    - preferred: "help"      avoid: ["assist", "facilitate"]
  forbidden:    - "synergy"    - "paradigm shift"    - "game-changing"
doNot:  - pattern: "click here"    reason: "Poor accessibility"    suggestion: "Describe the destination"    severity: error
  - pattern: "\\b(obviously|simply|just)\\b"    isRegex: true    reason: "Can make users feel stupid"    severity: warning

Self-Hosting

Docker

bash
# Clone the repogit clone https://github.com/3DUNLMTD/stylemcp.gitcd stylemcp
# Set up environmentecho "STYLEMCP_API_KEY=$(openssl rand -hex 32)" > .env
# Run with Dockerdocker compose up -d
# Check healthcurl http://localhost:3000/health

Manual

bash
# Install dependenciesnpm install
# Buildnpm run build
# Start servernpm start

GitHub Actions

yaml
name: Brand Checkon: [pull_request]
jobs:  validate:    runs-on: ubuntu-latest    steps:      - uses: actions/checkout@v4
      - name: Validate copy        run: |          npx stylemcp validate src/copy/*.json \            --min-score 80 \            --format github

Environment Variables

VariableDescriptionDefault
PORTServer port3000
STYLEMCP_API_KEYAPI key for authentication(none)
GITHUB_WEBHOOK_SECRETGitHub webhook secret(none)

MCP Tools

When used as an MCP server, StyleMCP provides these tools:

ToolDescription
validate_textValidate text against brand rules
rewrite_to_styleRewrite text to match brand voice
get_voice_rulesGet voice and tone guidelines
get_copy_patternsGet approved copy patterns
get_cta_rulesGet CTA guidelines
get_tokensGet design tokens
list_packsList available style packs

What Gets Validated?

The saas pack checks for:

Vocabulary

  • Use simple words: "use" not "utilize", "help" not "assist"
  • Avoid jargon: "synergy", "leverage", "paradigm shift"
  • Avoid weak intensifiers: "very", "really", "extremely"

Patterns

  • No "click here" (accessibility issue)
  • No "we're sorry for any inconvenience" (corporate non-apology)
  • No double "please" (sounds desperate)
  • No starting with "Sorry" (lead with solutions)

CTAs

  • Avoid generic: "Submit", "OK", "Yes/No", "Click here"
  • Use specific actions: "Save", "Create", "Sign up", "Export"
  • Max 4 words

Constraints

  • Max 25 words per sentence
  • No exclamation marks (in most contexts)
  • First-person plural ("we", "our")
  • Oxford comma

License

MIT

來源:README.md,提交 fb5ea98

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.1.4最新Sep 16, 2026

評分

已滿足適用檢查項的 40%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。