IndieStack
Discovery layer between AI coding agents and 3,100+ developer tools. Search, compare, and get integration code for auth, payments, analytics, email, databases, and 25 other categories — so agents recommend existing tools instead of generating boilerplate.
README
IndieStack
A curated directory of 880+ indie tools with a built-in MCP server that lets AI coding assistants search the catalog before generating boilerplate.
Your AI is writing code you don't need. Instead of generating 47,000 tokens of analytics boilerplate, IndieStack finds an existing indie tool in 700 tokens.
MCP Server Quick Start
IndieStack is published on PyPI as a Model Context Protocol (MCP) server. Install it and connect it to your AI coding assistant in under a minute.
Claude Code
pip install indiestack
claude mcp add indiestack -- python -m indiestack.mcp_server
Cursor
Add to your .cursor/mcp.json:
{
"mcpServers": {
"indiestack": {
"command": "python",
"args": ["-m", "indiestack.mcp_server"]
}
}
}
Windsurf
Add to your ~/.windsurf/mcp.json:
{
"mcpServers": {
"indiestack": {
"command": "python",
"args": ["-m", "indiestack.mcp_server"]
}
}
}
Available Tools
The MCP server exposes two tools via stdio transport:
| Tool | Description |
|---|---|
search_indie_tools(query) |
Search the directory by keyword, category, or use case |
get_tool_details(slug) |
Get full details for a specific tool |
What It Does
IndieStack is a web directory and discovery platform for independent software products.
- Browse and search 130+ curated indie SaaS tools across categories like analytics, auth, payments, email, and more
- MCP integration lets AI assistants recommend existing tools instead of generating boilerplate code
- Maker profiles for indie developers to showcase their products
- Alternatives pages for programmatic SEO (e.g., "IndieStack alternatives to Segment")
- Stack analyzer to evaluate tool combinations
- Stripe Connect payments for premium placements and Pro maker accounts
- Reviews, wishlists, and changelogs for community engagement
Project Structure
src/indiestack/
├── main.py # FastAPI app + route registration
├── db.py # SQLite database layer
├── auth.py # Authentication
├── payments.py # Stripe Connect integration
├── email.py # Transactional email (SMTP)
├── mcp_server.py # MCP server (PyPI package entry point)
├── routes/
│ ├── components.py # Shared UI components (page shell, nav, footer)
│ ├── landing.py # Homepage
│ ├── browse.py # Category browsing
│ ├── tool.py # Tool detail pages
│ ├── search.py # Search
│ ├── submit.py # Tool submission
│ ├── admin.py # Admin panel
│ ├── dashboard.py # User dashboard
│ ├── maker.py # Maker profiles
│ ├── alternatives.py# Programmatic SEO pages
│ ├── stacks.py # Stack analyzer
│ └── ... # Other routes
The frontend uses pure Python string templates with a shared component system -- no Jinja2 or JS framework required.
Self-Hosting
Requirements
- Python 3.11+
- SQLite
Setup
git clone https://github.com/Pattyboi101/indiestack.git
cd indiestack
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[server]"
Environment Variables
Create a .env file:
SECRET_KEY=your-secret-key
STRIPE_SECRET_KEY=sk_test_...
STRIPE_PUBLISHABLE_KEY=pk_test_...
SMTP_HOST=smtp.gmail.com
SMTP_USER=you@example.com
SMTP_PASSWORD=your-app-password
SMTP_FROM=you@example.com
Run
uvicorn src.indiestack.main:app --reload
The app will be available at http://localhost:8000.
Seed Data
python3 seed_tools.py
Populates the database with sample indie tools for development.
Deploy to Fly.io
fly deploy --remote-only
Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/your-feature) - Commit your changes
- Open a pull request
Please keep PRs focused and include a clear description of what changed and why.
License
MIT
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。