invoiceflow-mcp
AI-powered invoice automation. Create PDF invoices, predict late payment risk 0-100, auto-send reminders, reconcile Stripe/PayPal payments, track cash flow. 10 MCP tools, 4 resources.
README
InvoiceFlow MCP
AI-powered invoice automation for the Model Context Protocol
InvoiceFlow creates professional PDF invoices, predicts late payment risk using AI, auto-sends reminders, reconciles payments from Stripe/PayPal, and tracks your cash flow -- all through the MCP protocol.
Features
- Professional PDF invoices with line items, tax, discounts, multi-currency (10 currencies)
- AI risk prediction (0-100) based on invoice amount, client history, due date, reminder history
- Smart reminders with escalation based on risk level
- Payment reconciliation matching Stripe/PayPal payments to invoices by amount + email
- Cash flow reporting with collection rate, projected income, client breakdown
- Client management with automatic payment history tracking
- Sequential invoice numbers (INV-2026-0001, INV-2026-0002, ...)
- 10 MCP tools + 4 MCP resources covering the full invoicing lifecycle
Quick Start
Install from MCPize Marketplace
- Search for InvoiceFlow MCP on mcpize.com
- Click Install and select your subscription tier
- Tools and resources are automatically available in any MCP-compatible client
Build from Source
git clone https://github.com/enzoemir1/invoiceflow-mcp.git
cd invoiceflow-mcp
npm ci
npm run build
Add to your MCP client config:
{
"mcpServers": {
"invoiceflow": {
"command": "node",
"args": ["path/to/invoiceflow-mcp/dist/index.js"]
}
}
}
Tools
client_manage
Create a new client. Required before creating invoices.
invoice_create
Create an invoice with line items. Auto-calculates subtotal, tax, discounts, and total. Generates sequential invoice numbers (INV-YYYY-NNNN).
invoice_send
Send an invoice PDF via email (requires SENDGRID_API_KEY). Updates status to "sent".
invoice_list
Filter invoices by status, client, amount range, date range, or overdue status. Supports pagination.
invoice_mark_paid
Mark an invoice as paid (full or partial). Updates client payment history automatically.
invoice_remind
Send a payment reminder. Increments reminder count. Supports custom messages.
invoice_risk
AI-powered late payment risk prediction (0-100). Returns risk level, factor breakdown, recommended action, next reminder date.
cashflow_report
Generate cash flow summary: total invoiced, collected, outstanding, overdue, collection rate, 30-day projection.
payment_reconcile
Match incoming payment to invoice by amount and payer email. Auto-marks as paid.
Resources
| Resource | Description |
|---|---|
invoices://pending |
All unpaid invoices |
invoices://overdue |
Invoices past due date |
invoices://stats |
Monthly cash flow summary |
clients://list |
All clients with payment history |
Risk Prediction Engine
Scores invoices 0-100 using 4 weighted factors:
| Factor | Weight | What It Measures |
|---|---|---|
| Invoice Amount | 20% | Higher amounts = higher risk |
| Client History | 35% | Pay rate, late payments, avg days |
| Due Date | 30% | Days until/past due |
| Reminders | 15% | Reminders already sent |
Risk Levels: Low (0-30), Medium (31-60), High (61-100)
Integrations
- SendGrid -- Set SENDGRID_API_KEY for email invoices/reminders
- Stripe -- Set STRIPE_API_KEY for payment reconciliation
- PayPal -- Set PAYPAL_CLIENT_ID + PAYPAL_CLIENT_SECRET
Currencies
USD, EUR, GBP, CAD, AUD, JPY, CHF, TRY, BRL, INR
Pricing
| Tier | Price | Invoices/month | Features |
|---|---|---|---|
| Free | $0 | 5 | Basic PDF invoices |
| Pro | $15/mo | 100 | AI risk, reminders, Stripe sync |
| Business | $30/mo | Unlimited | Multi-currency, reconciliation, cash flow |
Available on MCPize Marketplace.
Development
npm run dev # Hot reload
npm run build # Production build
npm test # Run tests
npm run inspect # MCP Inspector
License
MIT License. See LICENSE for details.
Built by Automatia BCN.
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。