saas-brain-mcp

saas-brain-mcp

Open-source MCP server for Claude AI that connects Stripe and Supabase to enable natural language SaaS analytics, including churn analysis, subscription tracking, and revenue insights.

Category
访问服务器

README

SaaS Brain MCP

Ask questions about your SaaS business in plain English using Claude AI.

"Who is about to churn?" • "What's my revenue this week?" • "Who are my best customers?"

No dashboards. No SQL. Just ask.

What it does

SaaS Brain is an MCP (Model Context Protocol) server that connects Claude AI to your Stripe and Supabase data. Ask natural language questions and get intelligent business insights instantly.

Available tools

Tool What it answers
getRevenue Total revenue for any date range
getTopCustomers Highest spending customers
getActiveSubscriptions All active subscribers + plan info
getInactiveUsers Users who haven't logged in for N days
getUserActivity Last login + activity for a specific user
getChurnRiskUsers Paying users who have gone inactive
getHighValueUsers Customers above a spend threshold
getHighValueAtRiskUsers High spenders who are now inactive

Example questions you can ask Claude

  • "What's my revenue from January to March?"
  • "Show me my top 5 customers by spend"
  • "Which users are at risk of churning?"
  • "Who pays the most but hasn't logged in recently?"
  • "Give me a full health report of my SaaS"

Tech stack

  • Java 17 + Spring Boot
  • Stripe API
  • Supabase REST API
  • Docker
  • MCP Protocol (JSON-RPC 2.0)

Prerequisites

  • Java 17+
  • Maven
  • A Stripe account (free, test mode works)
  • A Supabase project (free tier works)
  • A Claude.ai account (free tier works)

Setup

1. Clone the repo

git clone https://github.com/Mohd16kaif/saas-brain-mcp.git
cd saas-brain-mcp

2. Add your API keys

Create src/main/resources/application.properties:

server.port=8080
spring.application.name=saas-brain-mcp

stripe.api.key=sk_test_YOUR_STRIPE_KEY
supabase.url=https://YOUR_PROJECT.supabase.co
supabase.key=YOUR_SERVICE_ROLE_KEY

Get your keys from:

  • Stripe: dashboard.stripe.com → Developers → API Keys
  • Supabase: app.supabase.com → Settings → API → service_role key

3. Run locally

mvn spring-boot:run

Test it:

curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'

Deploy to Render (free, 24/7)

1. Fork this repo on GitHub

2. Create a new Web Service on Render

  • Go to render.com → New → Web Service
  • Connect your forked repo
  • Language: Docker
  • Branch: main
  • Instance Type: Free

3. Add environment variables in Render

Key Value
STRIPE_API_KEY your Stripe key
SUPABASE_URL your Supabase project URL
SUPABASE_KEY your Supabase service_role key

4. Deploy

Render builds and deploys automatically. Your server will be live at:

https://your-service-name.onrender.com

Connect to Claude.ai

  1. Go to claude.ai → Settings → Connectors
  2. Click Add custom connector
  3. Name: saas-brain
  4. URL: https://your-render-url.onrender.com/mcp
  5. Save and enable in chat

Then just ask Claude anything about your business.

Connect to Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "saas-brain": {
      "type": "http",
      "url": "https://your-render-url.onrender.com/mcp"
    }
  }
}

File location:

  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Important notes

  • Use Supabase's service_role key (not the anon key) needed to query auth.users
  • Churn detection works by matching emails between Stripe and Supabase make sure users sign up with the same email in both
  • Free Render instances sleep after 15 minutes of inactivity first request may take 30 seconds to wake up

Cost

$0 Stripe test mode is free, Supabase free tier is permanent, Render free tier is sufficient for personal use.

License

MIT free to use, modify, and deploy.

Built by

Mohd. Kaif Shaikh GitHub

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选