What is MCP Send to Feishu?
MCP Send to Feishu is a server application that sends notifications to Feishu and WebSocket when agent tasks are completed, facilitating real-time communication and logging.
How to use MCP Send to Feishu?
To use MCP Send to Feishu, clone the repository, install the necessary packages, and configure the server with your Feishu webhook and WebSocket server details. You can then run the server and trigger notifications by adding specific prompts in your AI tasks.
Key features of MCP Send to Feishu?
- Sends notifications to Feishu webhook upon task completion.
- Sends notifications to a WebSocket server.
- Logs all notifications to a local file in JSON format.
- Integrates with various LLM clients based on the standard MCP protocol.
Use cases of MCP Send to Feishu?
- Automating task completion notifications in team collaboration tools.
- Real-time updates for project management applications.
- Logging notifications for auditing and monitoring purposes.
FAQ from MCP Send to Feishu?
- Can MCP Send to Feishu be used with any task automation tool?
Yes! It can be integrated with various LLM clients and task automation tools.
- Is there a logging feature?
Yes! All notifications are logged to a local file for record-keeping.
- What programming language is used for MCP Send to Feishu?
The project is developed in Python.
MCP Send to Feishu Server
A MCP server that sends notifications to Feishu and WebSocket when agent tasks are completed.
Features
- Send notifications to Feishu webhook when tasks are completed
- Send notifications to WebSocket server
- Log all notifications to a local file
- Based on standard MCP protocol, integrates with various LLM clients
Installation
Install using uv package manager
git clone https://github.com/byom/mcp_server_send_to_feishu.git
cd mcp_server_send_to_feishu
uv venv
source .venv/Scripts/activate
uv pip install mcp-server-send-to-feishu
# or
pip install mcp-server-send-to-feishu
After installation, call the module directly to check if installation was successful:
python -m mcp_server_send_to_feishu
This module accepts --debug or --file option, we can use it like:
python -m mcp_server_send_to_feishu --debug
python -m mcp_server_send_to_feishu --debug --log-file=path/to/logfile.log
Configuration
Feishu Webhook
The server is pre-configured with a Feishu webhook URL:
https://www.feishu.cn/***
WebSocket Server
By default, the server connects to:
ws://localhost:8765
Usage
Using with Claude Desktop:
Find the configuration file claude_desktop_config.json
{
"mcpServers": {
"NotificationServer": {
"command": "uv",
"args": [
"--directory",
"path/to/your/mcp_server_send_to_feishu project",
"run",
"mcp-server-send-to-feishu",
]
}
}
}
If installed globally, you can also use the python command:
{
"mcpServers": {
"NotificationServer": {
"command": "python",
"args": [
"-m",
"mcp_server_send_to_feishu",
]
}
}
}
Using with Cursor:
Find the configuration file ~/.cursor/mcp.json or your_project/.cursor/mcp.json
{
"mcpServers": {
"NotificationServer": {
"command": "uv",
"args": [
"--directory",
"path/to/your/mcp_server_send_to_feishu project",
"run",
"mcp-server-send-to-feishu",
]
}
}
}
After configuration, simply add a prompt like finally, send me a notification when task finished. at the end of your task input to the AI to trigger notifications.
In Cursor, you can add this prompt as a rule in Cursor Settings -> Rules so you don't have to type it manually each time.
Notification Format
Feishu Webhook
{
"msg_type": "text",
"content": {
"text": "title\nmessage"
}
}
WebSocket
{
"type": "notification",
"title": "title",
"message": "message"
}
Local Log File
Notifications are logged to notifications.log in JSON format:
{
"title": "title",
"message": "message",
"timestamp": "2024-04-14 12:34:56.789012"
}
License
MIT
Contributions
Issues and pull requests are welcome!