MCP Server for Alibaba Cloud Qwen-MT machine translation
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"qwen-mt-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# qwen-mt-mcp MCP Server for Alibaba Cloud Qwen-MT machine translation. Supports 92 languages, glossary terms, translation memory, and domain hints. ## Installation ```bash pip install qwen-mt-mcp ``` Or with [uv](https://docs.astral.sh/uv/): ```bash uv pip install qwen-mt-mcp ``` ## Configuration | Environment Variable | Required | Default | Description | |---------------------|----------|---------|-------------| | `DASHSCOPE_API_KEY` | Yes | — | Alibaba Cloud DashScope API Key | | `QWEN_MT_REGION` | No | `beijing` | API region: `beijing` or `singapore` | | `QWEN_MT_DEFAULT_MODEL` | No | `qwen-mt-plus` | Default model: `qwen-mt-plus` / `qwen-mt-flash` / `qwen-mt-lite` | ## MCP Client Setup ### Claude Desktop / Cursor Add to your MCP config: ```json { "mcpServers": { "qwen-mt": { "command": "uvx", "args": ["qwen-mt-mcp"], "env": { "DASHSCOPE_API_KEY": "sk-your-key" } } } } ``` Or if installed locally: ```json { "mcpServers": { "qwen-mt": { "command": "uv", "args": ["run", "--directory", "/path/to/MT-mcp", "qwen-mt-mcp"], "env": { "DASHSCOPE_API_KEY": "sk-your-key" } } } } ``` ## Tools ### `translate` Translate text between languages. **Parameters:** | Parameter | Type | Required | Description | |-----------|------|----------|-------------| | `text` | string | Yes | Text to translate (max 8192 tokens) | | `target_lang` | string | Yes | Target language name, e.g. `"English"`, `"Chinese"` | | `source_lang` | string | No | Source language, default `"auto"` for auto-detection | | `model` | string | No | `qwen-mt-plus` (best quality), `qwen-mt-flash` (balanced), `qwen-mt-lite` (fastest) | | `terms` | array | No | Glossary: `[{"source": "term", "target": "translation"}]` | | `tm_list` | array | No | Translation memory: `[{"source": "src sentence", "target": "tgt sentence"}]` | | `domains` | string | No | Domain hint in English, e.g. `"IT"`, `"legal"`, `"medical"` | #…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.