MCP Environment & Installation Manager
A unified control center for managing MCP servers, providing tooling for environment variable management, profile-based configurations, and local package installation automation.
Tools
set-env-var
export-env-vars
list-env-vars
get-env-var
delete-env-var
create-profile
update-profile
list-installed-mcps
list-profiles
get-profile
delete-profile
activate-profile
get-active-profile
get-mcp-package
install-mcp
update-mcp
uninstall-mcp
configure-installation
get-installation-settings
configure-watcher
get-watcher-config
enable-auto-localize
configure-notifications
localize-mcp-server
README
MCP Environment & Installation Manager
A unified control center for managing MCP servers and their configurations. This MCP server provides tooling for environment variable management, profile-based configurations, and local package installation automation.
Features
- Environment Variable Management: Securely store and manage environment variables for your MCP servers
- Profile System: Create different profiles for different projects or environments
- Local Package Installation: Automatically install MCP packages locally
- Configuration Watching: Monitor MCP configurations and adapt to changes
- Auto-Configuration: Automatically update configurations to use locally installed packages
Installation
Node.js Installation
# Global installation
npm install -g @devlimelabs/mcp-env-manager
# Or using yarn
yarn global add @devlimelabs/mcp-env-manager
# Or using pnpm
pnpm add -g @devlimelabs/mcp-env-manager
Docker Installation
# Clone the repository
git clone https://github.com/devlimelabs/master-mcps.git
cd master-mcps/packages/mcp-env-manager
# Build and run with Docker
npm run docker:build
npm run docker:run
# Or using Docker Compose
npm run compose:up
Configuration
Create a .env file based on the .env.example template:
# Copy the example configuration
cp .env.example .env
# Edit the configuration
nano .env
Important Environment Variables
MCP_ENV_ENCRYPTION_KEY: Required for encrypting sensitive valuesMCP_ENV_STORAGE_DIR: Directory for storing configuration (default: ~/.mcp-env-manager)
Usage
Command Line Interface
# Start the MCP server with stdio transport (for Claude, Cursor integration)
mcp-env-manager
# Start with SSE transport (for web integration)
mcp-env-manager --sse --port 3000
With Claude for Desktop
- Run the provided setup script:
npm run setup:claude
Or manually add the Environment Manager to your Claude for Desktop configuration file:
{
"mcpServers": {
"env-manager": {
"command": "mcp-env-manager",
"displayName": "Environment & Installation Manager"
}
}
}
- Restart Claude for Desktop and start using the Environment Manager tools.
With Cursor
Add the Environment Manager to your Cursor MCP configuration file:
{
"mcpServers": {
"env-manager": {
"command": "mcp-env-manager"
}
}
}
Tool Examples
Managing Environment Profiles
> create-profile
name: "Development Environment"
description: "Configuration for local development"
> list-profiles
Managing Environment Variables
> set-env-var
profileId: "development-environment-12345"
key: "API_KEY"
value: "your-api-key-here"
sensitive: true
> list-env-vars
profileId: "development-environment-12345"
> activate-profile
profileId: "development-environment-12345"
Managing MCP Installations
> install-mcp
packageName: "@modelcontextprotocol/server-filesystem"
> list-installed-mcps
> update-mcp
packageName: "@modelcontextprotocol/server-filesystem"
Configuration Watching
> configure-watcher
watchClaude: true
watchCursor: true
> enable-auto-localize
enabled: true
Development
# Install dependencies
npm install
# Start in development mode
npm run dev
# Run tests
npm test
# Build the package
npm run build
Known Limitations and Future Improvements
- SSE Transport: The current SSE transport implementation is incomplete and falls back to stdio. Further work is needed to make it fully functional for web integrations.
- Testing: The MCP server communicates via JSON-RPC over stdio which makes automated testing more complex. See testing_guide.md for manual testing procedures.
- Package Installation: Package installation depends on the local Node.js environment and should be tested with actual MCP packages.
Running Manual Tests
For manual testing details, see the Testing Guide.
Docker Deployment
The package includes a multi-stage Dockerfile and docker-compose.yml for easy deployment:
# Start the service with Docker Compose
docker-compose up -d
# View logs
docker-compose logs -f
# Stop the service
docker-compose down
Security Considerations
- The
MCP_ENV_ENCRYPTION_KEYshould be kept secure and not committed to version control - Sensitive values are encrypted at rest using the provided encryption key
- Use a strong, randomly-generated encryption key for production environments
Contributing
Contributions are welcome! Please see CONTRIBUTING.md for details.
License
MIT
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。