DingTalkMCPServer

# DINGTALK MCP - Call locally deployed MCP services through the DingTalk client AI assistant **Import the repository into your Python IDE project to start running without remote deployment** ## Main Features - Direct communication between DingTalk AI assistant and local services - Supports MCP protocol with multi-model configuration - Supports locally running MCP Service <div align="center"> <img src="app/resource/conversation.jpg" width="600" alt="Conversation Feature"> <br> <em>Conversation Feature</em> </div> ## Project Directory Structure ``` [ '|-- Project', ' |-- README.md', ' |-- main.py', ' |-- app', ' |-- api', ' | |-- __init__.py', ' | |-- dingtalk_client.py', ' |-- config', ' | |-- __init__.py', ' | |-- settings.py', ' |-- core', ' | |-- __init__.py', ' | |-- llm_service.py', ' | |-- mcp_server.py', ' | |-- message_service.py', ' |-- resource', ' | |-- DingTalkAgentConfig', ' | |-- conversation.jpg', ' |-- utils', ' |-- __init__.py', ' |-- logger.py', '' ] ``` ## 🛠️ Custom Function Development In the `app/core/mcp_server.py` file, you can add your own custom functions using the `@register_tool` decorator: ## Environment Requirements - Python > 3.10 - OpenSSL > 1.1 ### Using Local Environment 1. Install dependencies: ```bash Directly import using IDE ``` Contributions are welcome! Feel free to reach out! Contact email: miechalzhao@gmail.com