MCP Translation Text
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NIUTRANS_API_KEY | Yes | Your Niutrans API key from https://niutrans.com/cloud/account_info/info |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| translate_textA | 使用小牛翻译 API 将文本从 source 语种翻译到 target 语种。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| language_catalog | 提供小牛翻译支持的语种及别名列表。 返回内容包括所有语种的代码与中英文名称,以及可用的别名映射,可用于模型在翻译前完成语种推断。 |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single translate_text tool has a clearly defined purpose that is distinct by default.
The single tool name follows a clear verb_noun pattern (translate_text). With only one tool, consistency is inherently perfect as there are no other tools to compare against.
A single tool for a translation server feels thin and limited. While translation is a focused task, a more complete surface might include tools for language detection, batch translation, or translation history. The scope appears underdeveloped with just one tool.
The server covers basic text translation but has significant gaps. There's no tool for language detection, batch operations, or managing translations (e.g., getting supported languages, translation memory). This limits agent workflows and creates dead ends for more complex translation tasks.