Taiga UI MCP Server
Provides AI assistants with comprehensive access to Taiga UI components, enabling retrieval of component documentation, code examples, and migration guides via four MCP tools.
README
Taiga UI MCP Server
🚀 The fastest way to integrate Taiga UI components into your AI workflow
A Model Context Protocol (MCP) server that provides AI assistants with comprehensive access to Taiga UI components. Seamlessly retrieve Taiga UI components implementations for your AI-powered development workflow.
Key Features
- Docs + code snippets. Full Taiga UI markdown plus ready Angular examples in one place.
- Four MCP tools. Get structured overview with
get_overview, discover withget_list_components, fetch examples viaget_component_example, and access migration guides withget_migration_guide. - Configurable & lightweight. Swap source URL (stable/next) without local Angular install.
Requirements
- Node.js 18 or newer
- VS Code, Cursor, Windsurf, Claude Desktop, Goose or any other MCP client
Getting started
First, install the Taiga UI MCP server with your client.
Standard config works in most of the tools:
{
"mcpServers": {
"taiga-ui": {
"command": "npx",
"args": [
"@taiga-ui/mcp@latest",
"--source-url=https://taiga-ui.dev/llms-full.txt" // or file from /next version, if you want
]
}
}
}
Tools
<details> <summary><b>Core automation</b></summary>
get_overview- Returns structured documentation header: import map (all packages and their exports), code generation checklist, CDK types reference, common mistakes, and getting started guides.
- Always call this first before using other tools — it provides critical context for correct code generation (right packages, right types, common pitfalls).
- Output: JSON with
sectionsarray (Import Map, Code Generation Checklist, CDK Types Reference, Common Mistakes, Getting Started) andtotalComponentscount.
get_overview();
{
"title": "Taiga UI - Complete Documentation",
"sections": [
{
"title": "Import Map - Package Exports Reference",
"criticalNotices": ["Always import from the correct package. This is the #1 cause of compilation errors."],
"subsections": [...]
},
{ "title": "Code Generation Checklist", "subsections": [...] },
{ "title": "CDK Types Reference", "subsections": [...] },
{ "title": "Common Mistakes", "subsections": [...] },
{
"title": "Getting Started",
"description": "Installation and setup guides",
"subsections": [
{ "title": "addons", "content": ["npm i @taiga-ui/addon-charts ..."] },
{ "title": "app-standalone", "content": ["import {TuiRoot} from '@taiga-ui/core'; ..."] },
...
]
}
],
"totalComponents": 185
}
get_list_components { query?: string }- Lists component / section identifiers (with fuzzy substring filtering) along with basic metadata (category, package, type).
- Input: optional
querystring to filter IDs (case-insensitive substring). - Output: strictly structured JSON containing
items,total.
get_list_components();
{
"items": [
{
"id": "components/Alert",
"name": "Alert",
"category": "components",
"package": "CORE",
"type": "component"
},
{
"id": "components/Button",
"package": "CORE",
"type": "component",
"name": "Button",
"category": "components"
},
...
],
}
get_component_example { "names": ["...", "..."] }- Returns full markdown content for each resolved section (entire component documentation).
- Fuzzy name resolution: exact match, path segment, suffix, substring, and
Tui*variants. - Input:
{ names: string[] }(each name length ≥ 2). - Output:
resultsarray with objects:query,id(if resolved),package,type,suggestions(only when unresolved),content(array of code blocks, if examples exist). Top-level also includesmatched(count of resolved names).
get_component_example({names: ['Alert']});
{
"results": [
{
"query": "Alert",
"id": "components/Alert",
"package": "CORE",
"type": "component",
"content": ["# components/Alert\n- **Package**: ... (full component API, usage examples, ...)"]
}
],
"matched": 1
}
get_migration_guide- Returns the complete Migration Guide for Taiga UI version updates with pre-update checklist, migration instructions via schematics, and troubleshooting for common issues.
- Use this tool when you need to migrate between Taiga UI major versions or understand the migration process.
- Input: none (no parameters required).
- Output:
title,introductionwith version info, andsectionsarray with migration guidance, code blocks for CLI commands, and solutions for common problems.
get_migration_guide();
{
"title": "Migration Guide",
"introduction": [
"**Guide to update Taiga UI v{CURRENT_MAJOR} -> v{NEXT_MAJOR}**"
],
"sections": [
{
"title": "Before You Update",
"content": [...]
},
{
"title": "Updating",
"content": [...],
"codeBlocks": [...]
},
{
"title": "Troubleshooting",
"content": [...]
}
]
}
Tip: Start with
get_overviewto get import map and common mistakes, then useget_list_componentsto discover IDs,get_component_exampleto fetch full implementation snippets, andget_migration_guidefor version upgrade guidance.
</details>
Maintained
Taiga UI MCP is a part of Taiga UI libraries family which is backed and used by a large enterprise. This means you can rely on timely support and continuous development.
Authors
<table> <tr> <td align="center"> <a href="https://github.com/vladimirpotekhin" ><img src="https://github.com/vladimirpotekhin.png?size=200" width="100" style="margin-bottom: -4px; border-radius: 8px;" alt="Vladimir Potekhin" /><br /><b>Vladimir Potekhin</b></a > <div style="margin-top: 4px"> <a href="https://twitter.com/v_potekhin" title="Twitter" ><img width="16" src="https://raw.githubusercontent.com/MarsiBarsi/readme-icons/main/twitter.svg" /></a> <a href="https://github.com/vladimirpotekhin" title="GitHub" ><img width="16" src="https://raw.githubusercontent.com/MarsiBarsi/readme-icons/main/github.svg" /></a> <a href="https://t.me/v_potekhin" title="Telegram" ><img width="16" src="https://raw.githubusercontent.com/MarsiBarsi/readme-icons/main/send.svg" /></a> </div> </td> <td align="center"> <a href="https://github.com/mdlufy" ><img src="https://github.com/mdlufy.png?size=200" width="100" style="margin-bottom: -4px; border-radius: 8px;" alt="German Panov" /><br /><b>German Panov</b></a > <div style="margin-top: 4px"> <a href="https://twitter.com/mdlufy_" title="Twitter" ><img width="16" src="https://raw.githubusercontent.com/MarsiBarsi/readme-icons/main/twitter.svg" /></a> <a href="https://github.com/mdlufy" title="GitHub" ><img width="16" src="https://raw.githubusercontent.com/MarsiBarsi/readme-icons/main/github.svg" /></a> <a href="https://t.me/mdlufy" title="Telegram" ><img width="16" src="https://raw.githubusercontent.com/MarsiBarsi/readme-icons/main/send.svg" /></a> </div> </td> </tr> </table>
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。