DINGTALK MCP - 通过钉钉客户端AI助理调用本地私有部署的MCP服务
LocalAbout DINGTALK MCP - 通过钉钉客户端AI助理调用本地私有部署的MCP服务
A project for connecting DingTalk AI Agent to locally hosted private MCP services. It supports multi-model configuration and custom functions registered with a decorator.
Key features
- 01Direct DingTalk AI Agent access to local services
- 02Multi-model configuration
- 03Locally run MCP service
- 04Register custom functions with a decorator
Use cases
- 01Access locally deployed MCP services from DingTalk AI Agent
- 02Add custom functions to the service
MCP support
It provides a locally run MCP server for DingTalk AI Agent to call, with support for multi-model configuration.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEDINGTALK MCP - 通过钉钉客户端AI助理调用本地私有部署的MCP服务
将仓库导入python IDE工程即可启动运行，无需远端部署
##主要功能介绍
- 钉钉AI助理直通模式与本地服务通信
- 支持多模型配置的MCP协议
- 支持本地化运行的MCP Service
会话功能
项目目录结构
[
'|-- 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',
''
]
🛠️ 自定义函数开发
在 app/core/mcp_server.py 文件中，可以使用 @register_tool 装饰器添加您自己的自定义函数:
环境要求
- Python > 3.10
- OpenSSL > 1.1
使用本地环境
- 安装依赖:
直接采用IDE import即可
欢迎贡献！交流！联系邮箱 [email protected]
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.