Axolot MCP Server

Axolot MCP Server

Enables AI assistants to interact with Axolot CMS for content, design tokens, media, and module management with site context awareness.

Category
访问服务器

README

 Axolot MCP Server — AI-Native Headless CMS Bridge

NPM Version Model Context Protocol License

Axolot MCP Server (@axolot-ai/mcp-server) implements Anthropic's Model Context Protocol (MCP) to expose your website's database schema, layouts, media library, design tokens, and module tools directly to local AI assistants (Cursor, Claude Desktop, Antigravity, VS Code, Zed).

By running this server, you give your AI editor context-aware "hands" to fetch, build, and optimize pages, products, blog posts, and text slots within your exact design system constraints.


⚡ Key Capabilities

  • Surgical Content Orchestration: The AI can query pages, read slots, and register new visual slots (createSlot) dynamically as it writes Astro components.
  • Media Library Access: The AI browses available client assets, reading dimensions, file types, and vision-generated descriptions (getMedia) to select images automatically.
  • Brand Token Awareness: Fetches active color schemes, font families, and spacing rules (getDesignTokens) to write style-compliant Tailwind or CSS code.
  • Module Management: AI can query, create, or update articles in the Blog Pro module or products in the Tienda Online (E-commerce) module.

🔌 Setup & Configuration

Since the server is a Node.js CLI tool, the recommended way to run it is via npx, which requires zero local code installation or cloning.

A. Claude Desktop Integration

Add this snippet to your Claude Desktop configuration file (located at %APPDATA%\Claude\claude_desktop_config.json on Windows or ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "axolot-cms": {
      "command": "npx",
      "args": ["-y", "@axolot-ai/mcp-server"],
      "env": {
        "AXOLOT_API_URL": "https://api.axolotcms.com"
      }
    }
  }
}

B. Cursor Integration

  1. Open Cursor and go to Settings -> Features -> MCP.
  2. Click "+ Add New MCP Server".
  3. Configure it as:
    • Name: axolot-cms
    • Type: command
    • Command: npx -y @axolot-ai/mcp-server
  4. Add environment variables under settings if required, or log in interactively using the tools.

🛠️ Exposed AI Tools

Once connected, the AI will automatically invoke the following tools to fulfill your design prompts:

🔑 Authentication & Context

  • cms_auth_login: Triggers a secure authorization handshake URL in your browser.
  • cms_auth_status: Verifies connection status, user role, and active site.
  • cms_switch_site: Switches the active site context (site ID) when managing multiple client sites.

🎨 Brand & Design

  • getDesignTokens: Fetches active brand guidelines (colors, typography, spacing, border radius).
  • setDesignTokens: Updates brand tokens in the database to establish brand styling.
  • getSiteSettings: Fetches core business information (address, social links, email).

📝 Layouts & Visual Slots (Consolidated)

  • managePage: High-efficiency consolidated tool to list, get, create, update, or delete pages and their schemas.
  • getSlots: Reads details and values of slots on a specific page.
  • createSlot: Registers a new editable slot key (e.g. home.hero.title) in the database.

🛍️ Modules & Assets (Consolidated)

  • manageBlogPost: Consolidated tool to perform CRUD actions on blog posts (list, get, create, update, or delete).
  • manageProduct: Consolidated tool to perform CRUD actions on shop products (list, get, create, update, or delete).
  • getMedia: Lists media library files with WebP URLs and alt text descriptions.

🔒 Security & Sandboxing

The MCP server runs locally on your machine under your user context, connecting to the API via StdIO. It stores session authentication tokens securely in your user home directory at ~/.axolot/mcp-auth.json (isolated by OS permissions). It never exposes public network ports or scans files outside your active development project directory.


🔗 Useful Links


📄 License

Distributed under the MIT License. See LICENSE for more information.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选