alibaba-cloud-mcpSAFE
MCP server for Alibaba Cloud DashScope by three.ws — Qwen chat, embeddings, and model discovery using your own Alibaba Cloud API key.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
@three-ws/alibaba-cloud-mcp
MCP server for Alibaba Cloud DashScope, Qwen chat, embeddings, and model discovery on your own account.
Install · Quick start · Tools · Models · three.ws
A Model Context Protocol server that exposes Alibaba Cloud's Qwen models, and anything else in your DashScope account, to MCP clients such as Claude Desktop, Claude Code, and Cursor. It talks directly to the DashScope OpenAI-compatible REST API with your own Alibaba Cloud API key: no intermediary backend, no telemetry, no mock data.
Community-built and not affiliated with Alibaba Cloud. Registry name: io.github.nirholas/alibaba-cloud.Install
npm install @three-ws/alibaba-cloud-mcp
Run it directly with npx (no install needed):
DASHSCOPE_API_KEY=sk-... npx @three-ws/alibaba-cloud-mcp
Quick start
With Claude Code, one command:
claude mcp add alibaba-cloud -e DASHSCOPE_API_KEY=sk-... -- npx -y @three-ws/alibaba-cloud-mcp
Or add the server to your MCP client config:
{
"mcpServers": {
"alibaba-cloudf3f3f035b635OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add alibaba-cloud-mcp --env DASHSCOPE_API_KEY=${DASHSCOPE_API_KEY} -- npx -y @three-ws/[email protected]Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
.nojekyll
@modelcontextprotocol/sdk, zod
Gates applied: no_behavioural_pass.
f3f3f035b635full audit observations/trust-audit/mcp-server/nirholas__alibaba-cloud-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | f3f3f035b635 | SAFE | B | 89 | first audit |
Questions
What is the alibaba-cloud-mcp MCP server?
MCP server for Alibaba Cloud DashScope by three.ws — Qwen chat, embeddings, and model discovery using your own Alibaba Cloud API key.
Is alibaba-cloud-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does alibaba-cloud-mcp need?
It reads DASHSCOPE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does alibaba-cloud-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @three-ws/alibaba-cloud-mcp at 0.1.4.
How current is this page?
The grade is for one exact copy of the source (f3f3f035b635), read on 2026-10-10. The repository is watched and re-audited when it changes.