mcp-server
A Python Model Context Protocol (MCP) server suite that exposes Huawei Cloud services as MCP tools, enabling AI agents to manage cloud resources (e.g., ECS, OBS, GaussDB and many other Huawei Cloud products) through standardized MCP transports such as http/sse/stdio.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Uses Huawei Cloud AK/SK via environment variables (better than hardcoding), but README does not describe MCP endpoint auth, TLS requirements per transport, secret logging prevention, or per-tool/endpoint authorization scopes. Strong risk if the MCP server is network-accessible without controls; relies heavily on least-privilege AK/SK permissions.
⚡ Reliability
Best When
You want an on-prem/local MCP server that can translate agent tool calls into Huawei Cloud API actions with centralized configuration via YAML and environment-based credentials.
Avoid When
You need a managed SaaS API with documented SLAs, centralized rate-limit guarantees, or fine-grained OAuth-style access control at the MCP endpoint.
Use Cases
- • Letting an AI agent perform controlled Huawei Cloud resource management via MCP tools
- • Automating infrastructure and operations tasks (create/delete/modify) on Huawei Cloud services
- • Integrating Huawei Cloud actions into agent workflows through an MCP marketplace/client (e.g., Cline)
Not For
- • Untrusted/public exposure without network controls or authentication beyond Huawei credentials
- • Running without strict scope limitations, auditing, or least-privilege credentials
- • Use as a general-purpose cloud SDK replacement when you need REST/SDK-style ergonomics
Interface
Authentication
Authentication appears to be done by providing Huawei Cloud credentials to the MCP server via environment variables; the README does not describe endpoint-level auth or MCP client authentication.
Pricing
Open-source project; costs depend on Huawei Cloud usage and any hosting you provide for the MCP server.
Agent Metadata
Known Gotchas
- ⚠ Tool side-effects: cloud operations may be non-idempotent (e.g., create/delete) unless each tool is implemented with idempotency semantics
- ⚠ You must ensure the AI agent has least-privilege Huawei Cloud permissions because the MCP server likely forwards actions using the provided AK/SK
- ⚠ Transport selection (http/sse/stdio) affects deployment and security; http exposure without proper network controls can be risky
- ⚠ Rate limiting/backoff behavior is not described in the provided materials
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for mcp-server.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.