LaunchFrame MCP
Provides AI agents with architectural knowledge and scaffolding tools for LaunchFrame projects, covering patterns for authentication, queues, webhooks, and module structures. It enables agents to retrieve project-specific implementation details and generate code snippets on demand to maintain consistency.
README
@launchframe/mcp
MCP server that gives AI agents (Claude Code, Cursor, etc.) architectural knowledge about your LaunchFrame project — auth patterns, entity conventions, queue usage, cron jobs, webhooks, and more.
Installation
Running launchframe init automatically configures this MCP server in your project. No manual setup needed.
What It Does
Instead of bloating CLAUDE.md with rules, agents call tools on demand to pull the exact pattern they need:
| Tool | Description |
|---|---|
auth_get_overview |
Auth system, guard hierarchy, session flow |
auth_get_decorator_usage |
Exact decorator for a given auth need |
auth_get_guard_usage |
Guard class + import for admin/user/credits |
feature_gates_get_overview |
How feature gates are stored and queried |
feature_gates_get_check_pattern |
Copy-paste feature check snippet |
credits_get_deduction_pattern |
Decorator + guard for route-level credit deduction |
credits_get_add_pattern |
Code snippet for programmatic credit addition |
credits_get_monetization_strategies |
Overview of free/subscription/credits/hybrid modes |
queue_get_names |
Available Bull queues and their purpose |
queue_scaffold_producer |
Producer injection snippet for a given queue |
queue_scaffold_processor |
Processor class scaffold for a queue + job name |
webhook_get_architecture |
Receipt/processing separation, retry logic |
webhook_scaffold_handler |
Controller + processor scaffold for a provider/event |
cron_get_pattern |
Where crons live, available schedules, rules |
cron_scaffold_job |
Cron method scaffold to add to CronService |
module_get_structure |
NestJS module folder structure and conventions |
module_scaffold_nestjs |
Full module scaffold (module + service + controller + entity) |
entity_get_conventions |
TypeORM entity conventions and required decorators |
entity_scaffold_typeorm |
TypeORM entity file scaffold |
env_get_conventions |
Centralized .env rules and key variable reference |
variant_get_overview |
Base / Multi-tenant / B2B2C variant differences |
Manual Install
If you prefer a global install:
npm install -g @launchframe/mcp
Then in .mcp.json:
{
"mcpServers": {
"launchframe": {
"command": "launchframe-mcp"
}
}
}
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。