
mcp-angular-cli
mcp-angular-cli
Tools
ng_generate
Run 'ng generate' to create a new Angular artifact (component, service, etc.)
ng_add
Run 'ng add' to add a package to the Angular workspace
ng_new
Run 'ng new' to create a new Angular workspace
ng_run
Run 'ng run' to execute a custom architect target
ng_update
Run 'ng update' to update Angular packages and run migrations.
README
Angular CLI MCP Server 🅰️
A Model Context Protocol server that provides Angular CLI and workspace automation capabilities. This server enables LLMs and agents to interact with Angular projects, generate components/services, add packages, create new workspaces, and run custom architect targets via the Angular CLI.
Features
-
Run
ng generate
to scaffold Angular artifacts (components, services, etc.) -
Run
ng add
to add packages to your Angular workspace -
Run
ng new
to create new Angular workspaces -
Run
ng run
to execute custom architect targets -
Run
ng update
to update Angular packages and dependencies -
All via the Model Context Protocol (MCP) for agent/LLM integration
Installation
You can install the package globally using npm:
npm install -g @talzach/mcp-angular-cli
Or use it locally in your project:
npm install --save-dev @talzach/mcp-angular-cli
Usage
You can run the server directly:
npx @talzach/mcp-angular-cli
Or, if you want to use it as a custom MCP server in your agent or tool, configure it like this:
Example MCP Configuration
{
"mcpServers": {
"angular-cli": {
"command": "npx",
"args": ["-y", "@talzach/mcp-angular-cli"]
}
}
}
Example Tool Usage
- Generate a component:
{ "schematic": "component", "name": "my-component", "appRoot": "/absolute/path/to/your/angular/project" }
- Add a package:
{ "package": "@angular/material", "appRoot": "/absolute/path/to/your/angular/project" }
- Create a new workspace:
{ "name": "my-workspace", "directory": "/absolute/path/to/where/you/want/it" }
- Run a custom architect target:
{ "target": "app:build:production", "appRoot": "/absolute/path/to/your/angular/project" }
Star this repo if you find it useful!
Publishing to npm
To publish a new version of this package to npm, run:
npm run publish-npm
This will automatically build the project and publish it as a public package.
Develop
If you want to test or develop this server locally, you need to point your MCP server configuration to your local build output. After building the project (e.g., with npm run build
), set your MCP server file (e.g., .mcp.json
or similar) to use the local dist/index.js
file:
{
"angular-cli": {
"command": "node",
"args": ["/path/to/your/mcp-angular-cli/dist/index.js"]
}
}
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。