Zoho CRM MCP Server
A Model Context Protocol server for integrating Zoho CRM with GenAI applications, enabling AI assistants to interact with CRM data through a standardized interface.
README
Zoho CRM MCP Server
<!-- mcp-name: io.github.asklokesh/zoho-crm-mcp-server -->
<div align="center">
Zoho Crm Mcp Server
</div>
A Model Context Protocol (MCP) server for integrating Zoho CRM with GenAI applications.
Overview
This MCP server provides seamless integration with Zoho CRM, enabling AI assistants and applications to interact with your CRM data through a standardized interface.
Features
- 🔐 OAuth 2.0 Authentication - Secure authentication with automatic token refresh
- 📊 Comprehensive CRM Operations - Full support for Leads, Contacts, Deals, and more
- ⚡ Rate Limiting - Built-in rate limiting to respect API quotas
- 🔄 Automatic Retry Logic - Intelligent retry mechanism with exponential backoff
- 🛡️ Error Handling - Robust error handling and logging
- 🎯 MCP Protocol Compliance - Full compliance with Model Context Protocol specification
- 🚀 Async Support - Asynchronous operations for better performance
Available Tools
The server exposes the following MCP tools:
- get_leads - Retrieve leads from Zoho CRM with pagination
- create_lead - Create new leads in Zoho CRM
- get_contacts - Fetch contacts with pagination support
- get_deals - Get deals from Zoho CRM
- search_records - Search across any module with custom criteria
Installation
From PyPI (when published)
pip install zoho-crm-mcp-server
From Source
git clone https://github.com/asklokesh/zoho-crm-mcp-server.git
cd zoho-crm-mcp-server
pip install -e .
Development Installation
pip install -e ".[dev]"
Configuration
1. Set Up Zoho OAuth Credentials
- Go to Zoho API Console
- Create a new Self Client application
- Note your Client ID and Client Secret
- Generate a refresh token with required scopes:
ZohoCRM.modules.ALLZohoCRM.settings.ALL
2. Create Environment Configuration
Copy the example configuration:
cp .env.example .env
Edit .env with your credentials:
ZOHO_CLIENT_ID=your_client_id_here
ZOHO_CLIENT_SECRET=your_client_secret_here
ZOHO_REFRESH_TOKEN=your_refresh_token_here
# Optional configurations
ZOHO_API_DOMAIN=https://www.zohoapis.com
RATE_LIMIT_REQUESTS=100
RATE_LIMIT_PERIOD=60
MAX_RETRIES=3
LOG_LEVEL=INFO
Usage
As a Standalone Server
zoho-crm-mcp
In Python Code
from zoho_crm_mcp import ZohoCRMMCPServer
import asyncio
async def main():
server = ZohoCRMMCPServer()
await server.run()
if __name__ == "__main__":
asyncio.run(main())
Using the Zoho CRM Client
from zoho_crm_mcp import ZohoCRMClient, Config
import asyncio
async def main():
config = Config()
client = ZohoCRMClient(config)
await client.initialize()
# Get leads
leads = await client.get_leads(page=1, per_page=50)
print(f"Found {len(leads['data'])} leads")
# Create a new lead
new_lead = await client.create_lead({
"Last_Name": "Doe",
"First_Name": "John",
"Email": "john.doe@example.com",
"Company": "Acme Corp"
})
# Search for records
results = await client.search_records(
"Leads",
"(Email:equals:john.doe@example.com)"
)
await client.close()
if __name__ == "__main__":
asyncio.run(main())
Development
Running Tests
pytest tests/ -v --cov=zoho_crm_mcp
Linting
ruff check src/ tests/
ruff format src/ tests/
Building
python -m build
CI/CD
This project includes GitHub Actions workflows for:
- ✅ Automated testing across Python 3.8-3.12
- 🔍 Code quality checks with Ruff
- 📦 Package building and validation
- 📊 Code coverage reporting
Architecture
zoho-crm-mcp-server/
├── src/zoho_crm_mcp/
│ ├── __init__.py # Package initialization
│ ├── server.py # MCP server implementation
│ ├── zoho_client.py # Zoho CRM API client
│ └── config.py # Configuration management
├── tests/ # Comprehensive test suite
├── .github/workflows/ # CI/CD pipelines
└── pyproject.toml # Project configuration
Error Handling
The server includes comprehensive error handling:
- Token Expiry: Automatic token refresh when tokens expire
- Rate Limiting: Respects API rate limits with intelligent backoff
- Network Errors: Automatic retry with exponential backoff
- Validation Errors: Clear error messages for invalid configurations
Logging
The server uses Python's built-in logging module. Configure log level via environment variable:
export LOG_LEVEL=DEBUG # Options: DEBUG, INFO, WARNING, ERROR, CRITICAL
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
Troubleshooting
Common Issues
Issue: ModuleNotFoundError: No module named 'mcp'
Solution: Install the MCP SDK: pip install mcp
Issue: Token refresh fails Solution: Verify your refresh token is valid and has the required scopes
Issue: Rate limit errors
Solution: Adjust RATE_LIMIT_REQUESTS and RATE_LIMIT_PERIOD in your .env file
Requirements
- Python 3.8+
- requests >= 2.25.0
- mcp >= 1.0.0
- python-dotenv >= 0.19.0
License
MIT License - see LICENSE file for details
Support
For issues, questions, or contributions, please visit:
Acknowledgments
- Model Context Protocol - MCP specification
- Zoho CRM API - API documentation
- All contributors who help improve this project
Made with ❤️ for the MCP community
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。