Integrates with Huawei Cloud CSS (Cloud Search Service) to manage and query cloud search resources.
Provides tools for querying and managing Huawei Cloud resources including ECS, VPC, RDS, EVS, ELB, OBS, EIP, DDS, CSS, DCS, CES, and others, with support for pricing queries and multi-region operations.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@huawei-cloud-ops-mcp-server list my ECS instances in Beijing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
基于 Model Context Protocol (MCP) 的华为云 API 调用服务器，为 AI 助手提供华为云资源查询、价格查询和管理能力。
API 调用: 支持查询和管理华为云资源（ECS、VPC、RDS、EVS、ELB、OBS、EIP、DDS、CSS、DCS、CES 等）
价格查询: 支持查询华为云服务价格信息，支持多条件过滤
工作流指导: 智能分析用户查询，提供工具调用建议
多区域支持: 支持华为云全球多个区域，自动处理 project_id 和 region 映射
文档集成: 内置 API 文档和价格结构文档，支持快速查询
Related MCP server: MCP Cloud Services Server
Python >= 3.11
华为云账号及访问密钥 (AK/SK)
安装依赖：
# 使用 uv (推荐)
uv sync
# 或使用 pip
pip install -e .配置环境变量（创建 .env 文件）：
HUAWEI_CLOUD_ACCESS_KEY=your_access_key
HUAWEI_CLOUD_SECRET_KEY=your_secret_key
# MCP 传输方式：stdio（默认）或 http（用于 Docker）
MCP_TRANSPORT=http
# 日志配置（可选）
# LOG_LEVEL=INFO
# LOG_FILE=logs/app.log构建镜像：
docker build -t huawei-cloud-ops-mcp-server .运行容器：
docker run -d --rm \
-e HUAWEI_CLOUD_ACCESS_KEY=your_access_key \
-e HUAWEI_CLOUD_SECRET_KEY=your_secret_key \
-e MCP_TRANSPORT=http \
-e MCP_HOST=0.0.0.0 \
-p 8000:8000 \
huawei-cloud-ops-mcp-serverMCP 客户端配置（HTTP 传输）：
{
"mcpServers": {
"huawei-cloud-ops": {
"url": "http://localhost:8000"
}
}
}启动服务器：
python -m huawei_cloud_ops_mcp_server
linux: nohup uv run python -m huawei_cloud_ops_mcp_server > /dev/null 2>&1 </dev/null &MCP 客户端配置（stdio 传输）：
{
"mcpServers": {
"huawei-cloud-ops": {
"command": "python",
"args": ["-m", "huawei_cloud_ops_mcp_server"]
}
}
}当前仅支持 GET 请求，POST/PUT/DELETE 暂不支持
区域名称使用完整中文（如 "华北-北京一"），支持模糊匹配
API 返回 JSON 字符串格式
日志文件默认保存在 logs/app.log
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A paid remote MCP for AI SDK data query MCP, built to return verdicts, receipts, usage logs, and aud
MCP server for AI dialogue using various LLM models via AceDataCloud
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/zhiyibaby/huawei-cloud-ops-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server