
Backstage MCP Server
Provides comprehensive Backstage framework knowledge and development assistance through an MCP server. Enables plugin development, API reference access, code scaffolding, and community resource discovery for Backstage customization.
README
Backstage MCP Server
The MCP server is essentially a complete Backstage consultant in your development environment! 🚀
A comprehensive Model Context Protocol (MCP) server providing extensive knowledge about Backstage for plugin development and customization.
Features
This MCP server provides access to:
- Backstage Overview: Core concepts, features, benefits, and architecture
- Plugin Development Guide: Complete guide for creating custom plugins
- API Reference: REST endpoints, GraphQL APIs, and client libraries
- Community Resources: Discord channels, common questions, and learning materials
- Code Examples: Practical examples for common development scenarios
- Plugin Scaffolding: Generate plugin templates with custom configurations
Available Tools
1. get_backstage_overview
Get comprehensive overview of Backstage framework.
- Optional
section
parameter:whatIsBackstage
,coreFeatures
,benefits
,architecture
2. get_plugin_development_guide
Get detailed plugin development guide.
- Optional
topic
parameter:overview
,gettingStarted
,pluginStructure
,commonPatterns
,apis
,testing
,deployment
,bestPractices
3. get_api_reference
Get Backstage API reference documentation.
- Optional
api
parameter:catalogApi
,scaffolderApi
,techDocsApi
,authApi
,searchApi
,proxyApi
,graphqlApi
4. get_community_resources
Get community resources and support information.
- Optional
category
parameter:officialChannels
,communityPlugins
,commonQuestions
,learningResources
,adoptionStories
,contributing
5. get_backstage_examples
Get code examples and samples.
- Optional
type
parameter:pluginExamples
,catalogExamples
,templateExamples
,configExamples
- Optional
specific
parameter for specific examples within a type
6. search_backstage_knowledge
Search across all knowledge bases.
- Required
query
parameter: search terms
7. get_plugin_scaffold_template
Generate plugin scaffold templates.
- Required
pluginType
:frontend
,backend
,fullstack
,common
- Required
pluginName
: name of your plugin - Optional
features
array:routing
,api-client
,entity-provider
,scaffolder-action
,search-collator
Installation
Option 1: Docker (Recommended for Sharing)
# Quick setup
./setup.sh
# Or manual setup
npm run docker:compose:up
Usage
With Cursor/Claude Desktop (Docker)
Add to your MCP configuration:
{
"mcpServers": {
"backstage": {
"command": "docker",
"args": ["exec", "-i", "backstage-mcp-server", "node", "dist/index.js"]
}
}
}
Sharing with Friends
See SHARING_GUIDE.md
for complete instructions on sharing this server with friends.
Knowledge Base Coverage
- Core Backstage Concepts: Software Catalog, Templates, TechDocs, Plugins
- Plugin Development: Frontend, backend, and full-stack plugin creation
- API Integration: REST APIs, GraphQL, client libraries
- Community Insights: Discord discussions, common questions, best practices
- Real Examples: Working code samples for typical scenarios
- Configuration: App config, authentication, integrations
Contributing
This knowledge base is continuously updated with the latest Backstage information. To contribute:
- Update knowledge files in
src/knowledge/
- Add new tools in
src/index.ts
- Test with real Backstage scenarios
- Submit pull requests
Resources
License
Apache 2.0
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。