Skip to main content
Glama
MatthewLaw1

Crew AI MCP Server

by MatthewLaw1

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

  1. 克隆或分叉此存储库

  2. 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

Related MCP server: CrewAI Enterprise MCP Server

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:

  1. 确保您的 OpenAI API 密钥设置正确

  2. 检查所有依赖项是否已安装( pip install -r requirements.txt

  3. 验证 MCP 设置文件是否存在且配置正确

  4. 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

  1. 分叉存储库

  2. 创建你的功能分支

  3. 进行更改

  4. 运行安装脚本来验证一切正常

  5. 提交拉取请求

F
license - not found
-
quality - not tested
C
maintenance

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MatthewLaw1/Near-Intents-MCP-Agentkit'

If you have feedback or need assistance with the MCP directory API, please join our Discord server