What is the maximum team size?
The maximum team size is configurable via the `MAX_CREW_SIZE` environment variable, with a default of 10.
@Hwani-Net
基本信息
Dynamic Team Collaboration MCP Server for Smithery - Flexible crew synchronization with priority-based task management
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"crew-sync-agent": {
"command": "python",
"args": [
"test_crew_sync.py"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Crew Sync Agent is a flexible, dynamic team collaboration system built for the Model Context Protocol (MCP). It allows for dynamic team composition and real-time synchronization of crew members for various projects, unlike traditional fixed-team approaches.
Test locally with python test_crew_sync.py. For deployment, create a GitHub repository and deploy to Smithery using smithery deploy https://github.com/username/crew-sync-agent, then configure environment variables in the Smithery dashboard. Use the provided tools (sync_crew, add_crew_member, list_crew, echo) to manage and synchronize team members.
The maximum team size is configurable via the `MAX_CREW_SIZE` environment variable, with a default of 10.
API keys are managed exclusively through environment variables (`OPENAI_API_KEY`, `ANTHROPIC_API_KEY`). No hardcoded secrets exist in the code, and Docker runs as a non-root user for additional security.
It provides `sync_crew` (synchronize team members for a task), `add_crew_member` (add a new member), `list_crew` (list current team), and `echo` (connection test).
Create a GitHub repository, then run `smithery deploy` with your repository URL. Configure required environment variables in the Smithery dashboard.
The system uses Python and environment variables for configuration. Optional AI services (OpenAI, Anthropic) require corresponding API keys. Docker is recommended for deployment.
An MCP (Model Context Protocol) server that helps AI assistants (like Claude) break down complex tasks into manageable steps, track progress, and manage a hierarchical task list.
Aider-MCP-Upgraded is a production-grade multi-agent AI coding system that combines Desktop Commander (DC) investigation capabilities with Aider's implementation power. Features 70%+ token reduction, modular architecture, and intelligent workflow automation through strategic agen
This repository contains hands-on projects, code examples, and deployment workflows. Explore multi-agent systems, LangChain, LangGraph, AutoGen, CrewAI, RAG, MCP, automation with n8n, and scalable agent deployment using Docker, AWS, and BentoML.
Multi-Agent AI Orchestration Workshop
This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
评论