QuickBooks Online MCP Server
Enables AI assistants to query and manage QuickBooks Online data through natural language, including customers, invoices, bills, vendors, accounts, and financial reports.
README
QuickBooks Online MCP Server
A Model Context Protocol (MCP) server for QuickBooks Online integration, enabling AI assistants like Claude to query and manage QuickBooks data through natural language.
Features
- Customers: List, search, and view customer details
- Invoices: Create and list invoices with filtering
- Bills: Track vendor bills and payables
- Vendors: Manage supplier information
- Accounts: View chart of accounts
- Reports: Generate Profit & Loss reports
Prerequisites
- Node.js 18+
- QuickBooks Online account
- Intuit Developer account with OAuth app
Quick Start
1. Clone the repository
git clone https://github.com/hakeemrabiuDFW/quickbooks-mcp-server.git
cd quickbooks-mcp-server
2. Install dependencies
npm install
3. Configure environment
cp .env.example .env
Edit .env with your QuickBooks credentials:
QUICKBOOKS_CLIENT_ID=your_client_id
QUICKBOOKS_CLIENT_SECRET=your_client_secret
QUICKBOOKS_REFRESH_TOKEN=your_refresh_token
QUICKBOOKS_COMPANY_ID=your_company_id
QUICKBOOKS_ENVIRONMENT=production
4. Build and run
npm run build
npm start
Getting QuickBooks Credentials
Step 1: Create Developer Account
- Go to developer.intuit.com
- Sign in or create account
- Create a new app (select QuickBooks Online API)
Step 2: Get Client Credentials
- In your app dashboard, find Client ID and Client Secret
- Add OAuth redirect URI:
http://localhost:3000/callback
Step 3: Get Refresh Token
- Use the OAuth Playground in Intuit Developer portal
- Or use a tool like qbo-oauth-tool
- Complete OAuth flow to get refresh token
Step 4: Find Company ID (Realm ID)
- Log into QuickBooks Online
- Company ID is in the URL:
https://qbo.intuit.com/app/...?realmId=COMPANY_ID
Claude Desktop Configuration
Add to your Claude Desktop config (~/.config/claude/claude_desktop_config.json):
{
"mcpServers": {
"quickbooks": {
"command": "node",
"args": ["/path/to/quickbooks-mcp-server/dist/index.js"],
"env": {
"QUICKBOOKS_CLIENT_ID": "your_client_id",
"QUICKBOOKS_CLIENT_SECRET": "your_client_secret",
"QUICKBOOKS_REFRESH_TOKEN": "your_refresh_token",
"QUICKBOOKS_COMPANY_ID": "your_company_id",
"QUICKBOOKS_ENVIRONMENT": "production"
}
}
}
}
Available Tools
| Tool | Description |
|---|---|
qbo_list_customers |
List customers with optional filtering |
qbo_list_invoices |
List invoices by customer, status, or date |
qbo_create_invoice |
Create a new invoice |
qbo_list_accounts |
View chart of accounts |
qbo_profit_loss_report |
Generate P&L report |
qbo_list_vendors |
List vendor/suppliers |
qbo_list_bills |
List bills/payables |
Example Usage
Once connected to Claude:
"Show me all open invoices"
"Create an invoice for customer ID 123 with a $500 cleaning service charge"
"Get the profit and loss report for Q4 2025"
"List all unpaid bills"
HTTP Transport
To run as HTTP server instead of stdio:
TRANSPORT=http PORT=3000 npm start
Railway Deployment
Deploy to Railway with one click or via CLI:
Option 1: Railway Dashboard
- Fork this repository
- Go to Railway and create a new project
- Select "Deploy from GitHub repo"
- Add environment variables in Railway dashboard:
QUICKBOOKS_CLIENT_IDQUICKBOOKS_CLIENT_SECRETQUICKBOOKS_REFRESH_TOKENQUICKBOOKS_COMPANY_IDQUICKBOOKS_ENVIRONMENT=production
- Railway will auto-deploy using the included Dockerfile
Option 2: Railway CLI
# Install Railway CLI
npm install -g @railway/cli
# Login and deploy
railway login
railway init
railway up
MCP Endpoint
Once deployed, your MCP endpoint will be:
https://your-app.railway.app/mcp
Health check available at:
https://your-app.railway.app/health
Docker Deployment (Local)
docker build -t quickbooks-mcp .
docker run -p 3000:3000 --env-file .env quickbooks-mcp
License
MIT
Author
Hakeem Rabiu - Martinez Cleaning LLC
Links
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。