Skip to main content

MCP Deploy Server

Project description

Cloud Studio MCP 部署服务

Python Version FastAPI

Cloud Studio MCP 部署服务是一个基于FastMCP的服务器,提供Cloud Studio工作空间的管理功能,包括创建工作空间、上传文件和执行命令等操作。

功能特性

  • 创建工作空间:创建新的Cloud Studio工作空间实例
  • 文件管理:上传文件到指定工作空间
  • 命令执行:在工作空间中执行shell命令
  • MCP集成:通过MCP协议提供标准化接口

安装指南

前置要求

  • Python 3.8+
  • API_TOKEN环境变量(Cloud Studio API访问令牌)

安装步骤

  1. 克隆仓库:

    git clone <repository-url>
    cd mcp_deploy
    
  2. 创建并激活虚拟环境:

    python -m venv .venv
    source .venv/bin/activate  # Linux/macOS
    .\.venv\Scripts\activate   # Windows
    
  3. 安装依赖:

    pip install -e .
    

配置说明

在运行服务前,需要设置以下环境变量:

export API_TOKEN="your_cloud_studio_api_token"
export region="ap-shanghai"  # 可选,默认为ap-shanghai

使用说明

启动服务

python -m mcp_deploy

API 文档

服务提供以下MCP工具:

1. 创建工作空间

create_workspace() -> dict

返回示例:

{
    "workspace_key": "ws-kmhhvqnlogr48",
    "webIDE": "https://ws-kmhhv1pyvc48--ide.ap-shanghai.cloudstudio.club"
}

2. 上传文件

write_files(workspace_key: str, region: str, files: list[File]) -> str

文件格式:

class File:
    save_path: str    # 文件保存路径
    file_content: str # 文件内容(UTF-8编码)

3. 执行命令

execute_command(workspace_key: str, region: str, command: str) -> str

示例:

execute_command("ws-xxxx", "ap-shanghai", "ls -al")

开发指南

项目结构

mcp_deploy/
├── __init__.py
├── __main__.py
├── mcp_handlers.py    # 核心业务逻辑
├── models.py          # 数据模型定义
└── server.py          # FastMCP服务器实现

测试

  1. 确保已设置API_TOKEN环境变量
  2. 运行测试命令:
    python -m pytest
    

贡献

欢迎提交Pull Request或Issue报告问题。

许可证

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_deploy-0.1.11.tar.gz (23.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_deploy-0.1.11-py3-none-any.whl (11.0 kB view details)

Uploaded Python 3

File details

Details for the file mcp_deploy-0.1.11.tar.gz.

File metadata

  • Download URL: mcp_deploy-0.1.11.tar.gz
  • Upload date:
  • Size: 23.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.14

File hashes

Hashes for mcp_deploy-0.1.11.tar.gz
Algorithm Hash digest
SHA256 63b4ee00e40c80625ae55a1a5e36e2712ecdb436cd1036e4bee51f4dac9642b8
MD5 4aeab9223cd49b5cbf8c89fb62ffefee
BLAKE2b-256 3c6cde23a75b357db2536a223642b9921d7d858cc25f5f13cadf4fbca3daf8da

See more details on using hashes here.

File details

Details for the file mcp_deploy-0.1.11-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_deploy-0.1.11-py3-none-any.whl
Algorithm Hash digest
SHA256 8a73b5e250684a55e9d5a47961ece4412274c17015f6935befcc8ca8ccf482de
MD5 f3a083310b777e7bf52c9fb4c36ec3e4
BLAKE2b-256 11a3b821558ea54354e33b4bc2a654a9ea352283bbfcc0dfcd12fd6fc12af8bf

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page