Fanbei
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FANBEI_TOKEN | No | Fanbei access token starting with `fb1.` (default valid for 30 days). Used directly as the stdio MCP server credential. | |
| Authorization | No | Bearer token used in the HTTP Authorization header for remote streamable-http access, e.g. `Bearer fb1.xxxxx`. | |
| FANBEI_PASSWORD | No | Fanbei account password. Used together with FANBEI_USERNAME to obtain an access token on first use. | |
| FANBEI_USERNAME | No | Fanbei account username. Used together with FANBEI_PASSWORD so the service can obtain and cache an access token on first use. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
翻呗（Fanbei）文档翻译服务。支持 DOCX / PPTX / PDF / XLSX / TXT，以及 ZIP/7Z/RAR 批量包； 老格式 .doc/.xls/.ppt 上传时自动转 OOXML。
典型流程：
fanbei_engines 看有哪些翻译引擎与单价（1 积分/页起）
fanbei_quote 按页数估积分，确认余额够用
fanbei_translate_document 上传并下单（默认自动确认开始翻译）
fanbei_task_status 轮询进度（status=3 即完成）
fanbei_download 取 10 分钟有效的下载链接，或直接存到本地
规则提醒： · 每页扣积分，扣费发生在下单那一刻；失败任务不会自动退款，需走客服申诉。 · 传统网页引擎（金山/阿里/有道）不支持术语表与全文上下文，长文质量低于模型档。 · 下载链接 10 分钟过期，需要时重新调用 fanbei_download 换新链接。
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fanbei_accountA | 查询当前令牌对应账号的积分余额、有效期与令牌到期时间。 |
| fanbei_enginesA | 列出可用于翻译的引擎（模型档与传统网页引擎）、每页积分与能力边界。code 用于其它工具的 engine 参数。 |
| fanbei_quoteA | 按页数与选项估算积分消耗，并检查余额是否够用。下单前先报个价。 |
| fanbei_translate_documentA | 上传一个文档并下单翻译。文件来源三选一：file_path（本地路径，stdio 模式用）、file_url（公网直链）、file_base64（≤50MB，远程模式用）。auto_confirm=True 会立刻扣积分并开始翻译；False 只上传返回 tranId。wait_seconds>0 会同步等待到完成或超时（超时仍可用 fanbei_task_status 继续查）。 |
| fanbei_task_statusA | 按 tranId 查单个任务的状态、进度百分比与子文件明细。status=3 表示翻译完成、可以下载。 |
| fanbei_list_tasksA | 分页列出我的翻译任务（默认只看在用的）。scope 可选 active/trash/all。 |
| fanbei_downloadA | 取成品的下载链接（10 分钟有效）。save_to 给本地目录时，stdio 模式下会直接把文件写盘并返回路径。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool maps to a distinct step in the translation workflow: quoting, ordering, single-task lookup, task listing, downloading, account balance, and engine discovery. The overlap between fanbei_quote and fanbei_translate_document is intentional (estimate vs. purchase) and clearly described.
All tools use a consistent fanbei_ snake_case prefix, but the patterns mix verb_noun (translate_document, list_tasks, task_status) with bare nouns (quote, download, account, engines). This is readable and predictable overall, with only minor deviations.
Seven tools is well-scoped for a document translation service and each tool covers a necessary workflow step. There is no obvious redundancy or filler.
The core lifecycle is covered: quote, order, check status, list tasks, and download, plus account and engine metadata. However, there is no cancel, delete, or restore tool despite fanbei_list_tasks exposing a trash scope, and no retry for failed tasks, which are minor but real dead ends.