
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"]
}
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.