Ignite UI CLI MCP

- Create project structure
- Add views with Ignite UI components (e.g. Combo, Grid or Chart)
- Add scenario based templates with multiple components (e.g. a dashboard)
- Build and install npm packages
- Select a theme, support for custom themes coming soon
- Step by step guide

- Angular
- React
- Web Components
- Blazor
- jQuery

This monorepo contains several packages that combine into theigniteui-cli:

Install the npm package as a global module:

To get a guided experience through the available options, simply run:

Generating projects and adding components

Create a new project passing name, framework and style theme.

ig new <project name> --framework=<framework> --type=<proj-type> --theme=<theme>

This will create the project and will install the needed dependencies.

ig new "IG Project" --framework=angular --type=igx-ts --template=side-nav

ig new "IG Project" --framework=react --type=igr-ts

Generate Ignite UI for Web Components project

ig new "IG Project" --framework=webcomponents

Add a new component or template to the project passing component ID and choosing a name.

ig add <component/template> <component_name>

The ID matches either a component ("grid", "combo", "text-editor", etc) or a predefined template. Predefined templates are framework/project specific and can provide predefined views with either multiple components or fulfilling a specific use case like "form-validation", "master-detail" and so on.

You will be prompted with two selections:

- AI agents— which tools to generate skill and instruction files for (Generic and Claude are selected by default)
- Coding assistants— which assistants to configure MCP servers for (general.mcp.jsonis selected by default, compatible with Claude Code, VS Code, and others)

ig ai-config --agents claude copilot generic --assistants vscode cursor

Theig newcommand also prompts for AI tool configuration as part of project creation.

The server runs over stdio and supports the following options:

ig mcp --remote <url> # Use a remote backend instead of the local SQLite database ig mcp --debug # Enable debug logging to mcp-server.log

For VS Code, theig ai-configcommand handles configuration automatically (see above). For other MCP clients (e.g., Claude Desktop, Cursor), configure them manually:

Build the MCP server and bundle it into the CLI:

cd packages/igniteui-mcp/igniteui-doc-mcp npm install npm run build cd ../../.. npm run build:mcp

Build the monorepo packages:npm run build

There is a predefined launch.config file for VS Code in the root folder, so you can use VS Code View/Debug window and choose one of the predefined actions. These include launching the step by step guide, create new project for a particular framework or add components.

cd packages/igniteui-mcp/igniteui-doc-mcp npm install # Install MCP-specific dependencies (separate from yarn workspaces) npm run build # Compile TypeScript + copy SQLite DB to dist/

The MCP server includes API reference docs for Angular, React, and Web Components. Angular and Web Components docs are generated from framework submodules via TypeDoc (submodules are auto-initialized by the build scripts). React uses a pre-built TypeDoc JSON model checked into git.

cd packages/igniteui-mcp/igniteui-doc-mcp npm run build:docs:angular # Angular: init submodule → TypeDoc → markdown + index.json npm run build:docs:webcomponents # Web Components: init submodule → build lib → TypeDoc → markdown + index.json npm run build:docs:all # Build both

Note:Web Components requires a one-time library build (npm run build:publishin the submodule) before TypeDoc can run. The build script handles this automatically.

npm run build:mcp # Compiles MCP server TypeScript and copies SQLite DB into dist/

npm run build:mcp npm run build node packages/cli/lib/cli.js mcp # Start via CLI # or directly: node packages/cli/mcp/dist/index.js # Start the bundled server

Building CLI package with bundled MCP server

The CLI package includes the MCP server as a bundled build artifact (not an npm dependency). To produce a complete CLI package with full MCP functionality, follow these steps:

# 1. Install monorepo dependencies yarn install # 2. Build the MCP server cd packages/igniteui-mcp/igniteui-doc-mcp npm install npm run build # Compile TypeScript + copy SQLite DB # 3. Build API reference docs (optional but recommended for full functionality) npm run build:docs:all # Init submodules + generate Angular + WC API docs via TypeDoc # 4. Bundle MCP into CLI (from repo root) cd ../../.. npm run build:mcp # Build MCP server # 5. Build all packages for publishing npm run build-pack

After step 5,npm packfrom the repo root orpackages/cli/will produce a tarball with the MCP server, documentation database, and API reference docs all included.

Skipping API docs:If you skip step 3, the MCP server will still work forlist_components,get_doc,search_docs, andget_project_setup_guidetools using the bundled SQLite database. Only theget_api_referenceandsearch_apitools require API docs.

The Ignite UI CLI tool uses Google Analytics to anonymously report feature usage statistics and basic crash reports. This data is used to help improve the Ignite UI CLI tools over time. You can opt out of analytics before any data is sent by using

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

One shared context layer for AI agents and humans — live API specs, DB schemas, and versioned contracts across repos so every agent and teammate works from the same source of truth.

Local stdio MCP server that lets AI coding agents read and maintain structured architecture, rules, and decisions directly from your repository.

The MCP server for Bitrix24 provides AI assistants with structured access to the Bitrix24 API. It delivers up-to-date method descriptions, parameters, and valid values, allowing assistants to work with precise data instead of guesswork. This reduces code errors and accelerates Bitrix24 integration development.

Official Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.

Remote, no-auth MCP server providing AI-powered codebase context and answers

Official Svelte MCP server, provides docs and suggestions on the generated code.

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

Documentation and assembly review for @nhtio/adk.

Structured .aide spec files that give AI agents progressive disclosure into your codebase architecture. 6 MCP tools, 8 slash commands, TUI wizard, multi-IDE support.