Umbraco MCP Server
Enables AI models to interact with Umbraco CMS, retrieving and manipulating content like document types and media via the Umbraco Management API.
README
Umbraco MCP Server

A Model Context Protocol (MCP) server implementation for Umbraco CMS, allowing LLMs to access and manipulate Umbraco content through standardized interfaces.
Overview
This repository provides a Model Context Protocol server that connects to Umbraco CMS, enabling AI models like Claude to:
- Retrieve content from Umbraco
- Execute operations against the Umbraco Management API
- Access document types, media, and other Umbraco resources
- Perform actions through standardized tool interfaces
Installation
# Clone the repository
git clone https://github.com/HappydanceLabs/umbraco-mcp-server.git
# Navigate to the project directory
cd umbraco-mcp-server
# Install dependencies
npm install
# Generate Umbraco API types
npm run generate:umbraco
# Start the development server
npm run dev
The server will be available at http://localhost:8787/
Connect the MCP Inspector
To explore the MCP API and test available resources and tools:
-
Start the MCP Inspector:
npm run mcp:inspector -
In the Inspector interface, switch the Transport Type to
SSEand enterhttp://localhost:8787/mcpas the URL. -
Click "Connect" and follow any authentication prompts.
-
Once connected, you can list and call the available resources and tools.
Connect to Claude Desktop
To use this MCP server with Claude:
-
Install Claude Desktop and follow Anthropic's MCP Quickstart
-
In Claude Desktop, go to Settings > Developer > Edit Config
-
Replace the configuration with:
{
"mcpServers": {
"umbraco": {
"command": "npx",
"args": [
"mcp-remote",
"http://localhost:8787/mcp"
]
}
}
}
- Restart Claude and you'll be able to use the Umbraco tools directly from Claude.
Deployment
-
Create a KV namespace for OAuth:
npx wrangler kv namespace create OAUTH_KV -
Add the KV namespace ID to
wrangler.jsonc -
Deploy to Cloudflare Workers:
npm run deploy -
Update your Claude configuration to use your deployed URL:
{ "mcpServers": { "umbraco": { "command": "npx", "args": [ "mcp-remote", "https://your-worker-url.workers.dev/sse" ] } } }
Project Structure
/src/api: Umbraco API clients and interfaces/src/resources: MCP resource implementations for reading Umbraco data/src/tools: MCP tool implementations for executing operations/src/helpers: Utility functions and shared code/src/types: TypeScript type definitions
Development
This project uses the Model Context Protocol TypeScript SDK and Cloudflare Agents SDK to implement resources and tools according to the MCP specification. Hosted and deployed on a Cloudflare Worker.
For more information on the MCP protocol, see the official documentation.
Debugging
If you encounter issues:
# Test direct connection to the MCP server
npx mcp-remote http://localhost:8787/sse
# Clear MCP authentication cache if needed
rm -rf ~/.mcp-auth
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。