mcp-server
@HuaweiCloudDeveloper
About mcp-server
Provide different cloud products MCP Server tools to help developers manage cloud resources with AI-agent
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-huaweiclouddeveloper": {
"command": "uv",
"args": [
"run",
"mcp-server-ecs"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is mCP-server?
Huawei MCP Server is a Model Context Protocol server built on Huawei Cloud services. It provides secure and controlled cloud access for large AI models, enabling AI assistants to operate Huawei Cloud resources within conversational workflows, supporting core services including ECS, OBS, GaussDB, and other widely‑used cloud products.
How to use mCP-server?
Install dependencies (Python 3.10+ and uv, or pip), then set the HUAWEI_ACCESS_KEY and HUAWEI_SECRET_KEY environment variables. Run a service with uv run mcp-server-ecs (or python run.py for individual services). Configure the server in an MCP client like Cline using a JSON object with the streamableHttp transport.
Key features of mCP-server
- Supports a wide range of Huawei Cloud services (ECS, OBS, GaussDB, and many more).
- Exposes cloud operations as MCP tools for AI assistants.
- Provides secure, controlled access to cloud resources.
- Supports multiple transports: HTTP, SSE, and stdio.
- Offers both
uvand Python/pip run methods. - Integrates with MCP marketplaces such as Cline.
Use cases of mCP-server
- Conversational creation and deletion of Elastic IP (EIP) instances.
- Database operational and maintenance conversations via DAS MCP.
- Managing networking resources like VPC, ELB, and NAT through chat.
- Automating container operations (e.g., CCE, SWR, CCI) in natural language.
- Orchestrating AI services (OCR, FRS, ModelArts) within a conversation.
FAQ from mCP-server
What cloud provider does the server work with?
It is built exclusively on Huawei Cloud services.
What environment variables are required?
You must set HUAWEI_ACCESS_KEY and HUAWEI_SECRET_KEY.
How do I run the server?
Recommended way: use uv run mcp-server-ecs. Alternatively, install with pip and run python run.py inside the desired service folder.
Which transports are supported?
The server supports http, sse, and stdio transports, configurable via the -t flag.
How can I use this server with Cline?
Configure your MCP client with a JSON object containing "url": "http://localhost:8888/mcp", "type": "streamableHttp", and any other optional fields.
Frequently asked questions
What cloud provider does the server work with?
It is built exclusively on Huawei Cloud services.
What environment variables are required?
You must set `HUAWEI_ACCESS_KEY` and `HUAWEI_SECRET_KEY`.
How do I run the server?
Recommended way: use `uv run mcp-server-ecs`. Alternatively, install with pip and run `python run.py` inside the desired service folder.
Which transports are supported?
The server supports `http`, `sse`, and `stdio` transports, configurable via the `-t` flag.
How can I use this server with Cline?
Configure your MCP client with a JSON object containing `"url": "http://localhost:8888/mcp"`, `"type": "streamableHttp"`, and any other optional fields.
Basic information
More Other MCP servers
Inbox Zero AI MCP
elie222The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
Reactive Resume
amruthpillaiA one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
MaxKB
1Panel-dev🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Comments