船员 AI MCP 服务器

使用 CrewAI 框架提供 AI 代理和任务管理功能的 MCP 服务器。

设置

克隆或分叉此存储库
运行安装脚本：

./crew.sh

安装脚本将：

安装所需的 Python 依赖项
为您的系统配置 MCP 设置文件
自动设置正确的路径

配置

在使用服务器之前，请设置您的 OpenAI API 密钥：

export OPENAI_API_KEY="your-api-key"

用法

该服务器提供三个主要工具：

1.创建代理

{
    "method": "call_tool",
    "params": {
        "name": "create_agent",
        "arguments": {
            "role": "researcher",
            "goal": "Research and analyze information effectively",
            "backstory": "An experienced research analyst"
        }
    }
}

2. 创建任务

{
    "method": "call_tool",
    "params": {
        "name": "create_task",
        "arguments": {
            "description": "Analyze recent market trends",
            "agent": "researcher",
            "expected_output": "A detailed analysis report"
        }
    }
}

3. 创建并管理团队

{
    "method": "call_tool",
    "params": {
        "name": "create_crew",
        "arguments": {
            "agents": ["researcher"],
            "tasks": ["Analyze recent market trends"],
            "verbose": true
        }
    }
}

示例用法

创建并运行完整的工作流程：

(echo '{"method": "call_tool", "params": {"name": "create_agent", "arguments": {"role": "researcher", "goal": "Research and analyze information effectively", "backstory": "An experienced research analyst"}}}'; echo '{"method": "call_tool", "params": {"name": "create_task", "arguments": {"description": "Analyze recent market trends", "agent": "researcher", "expected_output": "A detailed analysis report"}}}'; echo '{"method": "call_tool", "params": {"name": "create_crew", "arguments": {"agents": ["researcher"], "tasks": ["Analyze recent market trends"], "verbose": true}}}') | python3 src/crew_server.py

系统要求

Python 3.8 或更高版本
jq命令行工具（用于安装脚本）
安装了 Roo Cline 扩展的 VSCode

支持的平台

macOS
Linux
Windows（通过 Git Bash）

故障排除

如果您遇到任何问题：

确保您的 OpenAI API 密钥设置正确
检查所有依赖项是否已安装（ pip install -r requirements.txt ）
验证 MCP 设置文件是否存在且配置正确
确保 MCP 设置中的服务器路径与您的实际文件位置相符

贡献

分叉存储库
创建你的功能分支
进行更改
运行安装脚本来验证一切正常
提交拉取请求

This server cannot be installed

security - not tested

license - not found

quality - not tested

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

使用 CrewAI 框架实现 AI 代理和任务管理，允许用户在自动化工作流环境中创建和运行代理和任务。

Related MCP Servers

Linear MCP Server
ibraheem4
A
security
A
license
A
quality
Enables AI agents to manage issues, projects, and teams on the Linear platform programmatically.
Last updated -
7
83
50
JavaScript
MIT License
Targetprocess MCP Server
aaronsb
A
security
A
license
A
quality
Provides tools for interacting with Targetprocess, a project management and agile planning platform, enabling AI assistants to search, create, and update project entities with proper validation.
Last updated -
5
TypeScript
MIT License
Divide and Conquer MCP Server
landicefu
-
security
A
license
-
quality
Enables AI agents to break down complex tasks into manageable pieces using a structured JSON format with task tracking, context preservation, and progress monitoring capabilities.
Last updated -
12
2
JavaScript
MIT License
MCP Crew AI Server
adam-paterson
-
security
F
license
-
quality
A lightweight Python-based server designed to run, manage and create CrewAI workflows using the Model Context Protocol for communicating with LLMs and tools like Claude Desktop or Cursor IDE.
Last updated -
1
Python

View all related MCP servers

Crew AI MCP Server

船员 AI MCP 服务器

设置

配置

用法

1.创建代理

2. 创建任务

3. 创建并管理团队

示例用法

系统要求

支持的平台

故障排除

贡献

Related MCP Servers

Linear MCP Server

Targetprocess MCP Server

Divide and Conquer MCP Server

MCP Crew AI Server

Appeared in Searches

New MCP Servers

MCP directory API