Contentstack MCP Streamable HTTP Server

Contentstack MCP Streamable HTTP Server

A transport wrapper that exposes Contentstack MCP tools over HTTP instead of stdio to enable remote access and horizontal scaling. It acts as a proxy for the Contentstack MCP package, allowing browser-based and networked clients to interact with various Contentstack APIs.

Category
访问服务器

README

Contentstack MCP Streamable HTTP Server

DEPRECATED: Contentstack will build a Streamable http server soon

A Streamable HTTP transport wrapper for the @contentstack/mcp package. This server exposes all Contentstack MCP tools over HTTP instead of stdio, enabling remote access, horizontal scaling, and integration with browser-based and networked MCP clients.

How It Works

This server acts as a transparent proxy:

  1. Spawns @contentstack/mcp as a child process communicating via stdio
  2. Discovers all available tools from the child process
  3. Exposes them over Streamable HTTP transport at a single /mcp endpoint
  4. Forwards tool calls from HTTP clients to the underlying Contentstack MCP server

All tools from @contentstack/mcp are available — CMA, CDA, Analytics, BrandKit, Launch, DeveloperHub, Lytics, and Personalize.

Prerequisites

  • Node.js 18+
  • A Contentstack account with appropriate credentials
  • OAuth authentication completed (for CMA, Analytics, BrandKit, Launch, DeveloperHub, Personalize)

Setup

1. Install dependencies

npm install

2. Configure environment variables

Copy the example env file and fill in your credentials:

cp .env.example .env

Edit .env with your Contentstack credentials:

CONTENTSTACK_API_KEY=your_stack_api_key
GROUPS=cma

See Environment Variables for the full list.

3. Authenticate with OAuth

Before using CMA, Analytics, BrandKit, Launch, DeveloperHub, or Personalize tools, run the OAuth flow:

npm run auth

This stores your OAuth tokens locally for the child process to use.

4. Build and run

npm run build
npm start

For development with auto-reload:

npm run dev

The server starts on port 3000 by default.

Connecting a Client

Configure your MCP client to connect via Streamable HTTP. Example mcp-config.json:

{
  "mcpServers": {
    "contentstack": {
      "type": "streamable-http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

Cursor IDE

Add to your Cursor MCP settings (.cursor/mcp.json):

{
  "mcpServers": {
    "contentstack": {
      "type": "streamable-http",
      "url": "http://localhost:3000/mcp"
    }
  }
}

Environment Variables

Variable Required Description
PORT No Server port (default: 3000)
CONTENTSTACK_API_KEY Yes Your Stack API Key
CONTENTSTACK_DELIVERY_TOKEN CDA only Delivery token for Content Delivery API
CONTENTSTACK_BRAND_KIT_ID BrandKit only Brand Kit ID
CONTENTSTACK_LAUNCH_PROJECT_ID Launch only Launch Project ID
CONTENTSTACK_PERSONALIZE_PROJECT_ID Personalize only Personalize Project ID
LYTICS_ACCESS_TOKEN Lytics only Lytics access token
GROUPS No Comma-separated API groups to enable (default: cma). Options: cma, cda, analytics, brandkit, launch, developerhub, lytics, personalize, all

API Groups

Group Authentication Required Configuration
CMA OAuth Stack API Key
CDA Token-based Stack API Key + Delivery Token
Analytics OAuth Stack API Key
BrandKit OAuth Stack API Key + Brand Kit ID
Launch OAuth Stack API Key + Launch Project ID
DeveloperHub OAuth Stack API Key
Lytics Token-based Lytics Access Token
Personalize OAuth Stack API Key + Personalize Project ID

Endpoints

Method Path Description
POST /mcp MCP JSON-RPC requests (initialize, tool calls)
GET /mcp SSE stream for server-to-client notifications
DELETE /mcp Session termination
GET /health Health check with tool count and active sessions

License

MIT

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