OpenFeature MCP Server

OpenFeature MCP Server

Provides OpenFeature SDK installation guidance through MCP tool calls. Enables AI clients to fetch installation prompts and setup instructions for various OpenFeature SDKs across different programming languages and frameworks.

Category
访问服务器

README

OpenFeature MCP Cloudflare Worker

Warning

This project is in active development and intended for testing only. APIs, prompts, and behavior may change without notice. Do not use in production.

A simplified Model Context Protocol (MCP) server running on Cloudflare Workers that provides OpenFeature SDK installation guidance.

Features

  • No Authentication Required: Simplified implementation without OAuth or user management
  • OpenFeature SDK Installation Guides: Fetch installation prompts for various OpenFeature SDKs
  • MCP Protocol Support: Supports both SSE and JSON-RPC transports
  • Cloudflare Workers: Serverless deployment with global edge distribution

Configure your AI client

Use the hosted endpoint for this OpenFeature MCP worker: https://mcp-openfeature.devcycle.com/mcp

No authentication is required for this MCP.

Cursor

Add to ~/.cursor/mcp_settings.json:

{
  "mcpServers": {
    "OpenFeature": {
      "url": "https://mcp-openfeature.devcycle.com/mcp"
    }
  }
}

VS Code (Continue)

Add to .continue/config.json:

{
  "mcpServers": {
    "OpenFeature": {
      "url": "https://mcp-openfeature.devcycle.com/mcp"
    }
  }
}

Claude Code (CLI)

claude mcp add --transport http openfeature https://mcp-openfeature.devcycle.com/mcp

Then manage the connection in the CLI with /mcp.

Claude Desktop

Edit your Claude Desktop config and add:

{
  "mcpServers": {
    "openfeature": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp-openfeature.devcycle.com/mcp"]
    }
  }
}

Restart Claude Desktop after saving.

Windsurf

In the "Manage MCP servers" raw config, add:

{
  "mcpServers": {
    "OpenFeature": {
      "serverUrl": "https://mcp-openfeature.devcycle.com/mcp"
    }
  }
}

Reference installation patterns adapted from the DevCycle MCP getting started guide DevCycle MCP Getting Started.

Available Tools

install_openfeature_sdk

Fetches and returns OpenFeature SDK install prompt Markdown for a given guide from the bundled prompts.

Parameters:

  • guide (string enum): One of the supported guides listed below

Supported Guides (bundled):

  • android
  • dotnet
  • go
  • ios
  • java
  • javascript
  • nestjs
  • nodejs
  • php
  • python
  • react
  • ruby

Endpoints

  • /mcp - MCP JSON-RPC transport endpoint
  • /sse - MCP Server-Sent Events transport endpoint
  • /health - Health check endpoint
  • /info - Service information endpoint
  • / - Redirects to OpenFeature documentation

Development

Prerequisites

  • Node.js 18+
  • Yarn (using regular node_modules, not PnP)
  • Wrangler CLI

Setup

  1. Install dependencies:

    yarn install
    
  2. Add or edit install guides in the prompts/ folder (Markdown). These are bundled at build time.

  3. Build prompts bundle:

    yarn build-prompts
    
  4. Run locally:

    yarn dev
    
  5. Build for production:

    yarn build
    

Deployment

Deploy to Cloudflare Workers:

yarn deploy

Usage

The worker exposes MCP transport endpoints and simple health/info endpoints.

Examples

  1. Health:

    curl http://localhost:8787/health
    
  2. Info:

    curl http://localhost:8787/info
    
  3. MCP over HTTP (JSON-RPC) or SSE: Point your MCP-compatible client to /mcp (JSON-RPC) or /sse (SSE). The tool name is install_openfeature_sdk and requires an input object like { "guide": "react" }.

Architecture

This is a simplified version of the DevCycle MCP worker, with all authentication and project management features removed. It focuses solely on providing OpenFeature SDK installation guidance through MCP tool calls.

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