Zoho Books MCP Server
Enables AI assistants to manage Zoho Books accounting tasks such as invoices, contacts, expenses, and sales orders through natural language.
README
Zoho Books MCP Server
Connect your Zoho Books account to AI assistants like Claude Desktop through the Model Context Protocol (MCP).
Quick Start
1. Get Zoho API Credentials
- Go to Zoho API Console
- Create a "Server-based Application"
- Add redirect URI:
http://localhost:8099/callback - Select scope:
ZohoBooks.fullaccess.all - Save your Client ID, Client Secret, and Organization ID
2. Install via uvx
Add to your Claude Desktop configuration:
{
"mcpServers": {
"zoho-books": {
"command": "uvx",
"args": ["zoho-books-mcp"],
"env": {
"ZOHO_CLIENT_ID": "your_client_id",
"ZOHO_CLIENT_SECRET": "your_client_secret",
"ZOHO_REFRESH_TOKEN": "your_refresh_token",
"ZOHO_ORGANIZATION_ID": "your_organization_id",
"ZOHO_REGION": "US"
}
}
}
}
To get a refresh token: uvx zoho-books-mcp --setup-oauth
3. Restart Claude Desktop
Look for the 🔌 icon to verify connection.
Local Development
# Clone and setup
git clone https://github.com/kkeeling/zoho-mcp.git
cd zoho-mcp
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
# Run tests
pytest
# Run server
python server.py
For local development in Claude Desktop:
{
"mcpServers": {
"zoho-books": {
"command": "/path/to/venv/bin/python",
"args": ["/path/to/zoho-mcp/server.py"],
"env": {
"ZOHO_CLIENT_ID": "your_client_id",
"ZOHO_CLIENT_SECRET": "your_client_secret",
"ZOHO_REFRESH_TOKEN": "your_refresh_token",
"ZOHO_ORGANIZATION_ID": "your_organization_id",
"ZOHO_REGION": "US"
}
}
}
}
Available Features
Tools
Invoices: create_invoice, email_invoice, record_payment, send_payment_reminder, void_invoice, list_invoices, get_invoice, mark_invoice_as_sent
Contacts: create_customer, create_vendor, update_contact, delete_contact, email_statement, list_contacts, get_contact
Expenses: create_expense, update_expense, categorize_expense, upload_receipt, list_expenses, get_expense
Items: create_item, update_item, list_items, get_item
Sales Orders: create_sales_order, update_sales_order, convert_to_invoice, list_sales_orders, get_sales_order
Resources
- dashboard://summary - Business metrics overview
- invoice://overdue - Overdue invoices list
- invoice://unpaid - Unpaid invoices
- payment://recent - Recent payments
- contact://list - All contacts
- expenses://summary - Expense overview
Prompts
- invoice_collection_workflow - Complete invoice-to-payment cycle
- monthly_invoicing - Bulk invoice creation
- expense_tracking_workflow - Expense recording and categorization
Configuration
Regions
- US (zoho.com), EU (zoho.eu), IN (zoho.in), AU (zoho.com.au), JP (zoho.jp), UK (zoho.uk), CA (zoho.ca)
Troubleshooting
- Tools not showing: Restart Claude Desktop completely
- Auth errors: Regenerate refresh token with
uvx zoho-books-mcp --setup-oauth - Module errors: Ensure virtual environment is activated
Development & Releases
Creating a Release
To publish a new version to PyPI and create a GitHub release:
- Update version in
pyproject.toml - Update CHANGELOG.md with release notes
- Create and push a git tag:
git tag v0.1.0 git push origin v0.1.0 - Follow manual publishing steps in
PUBLISHING.mdto build, upload to PyPI, and create GitHub release
Prerequisites for Publishing
- PyPI account with API token
- GitHub CLI (
gh) installed and authenticated - Build tools:
pip install --upgrade pip build twine
License
MIT License - see LICENSE file for details.
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。