PaperBridge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PAPERBRIDGE_HOME | No | Overrides the data directory (default: ~/.paperbridge/) containing session.json, login-browser/, and config.json. | |
| PAPERBRIDGE_BROWSER | No | Specifies the browser to use: chrome, msedge, or chromium. Defaults to finding system Chrome or Edge. | |
| PAPERBRIDGE_DOWNLOADS | No | Overrides the default PDF download directory (default: ~/Documents/PaperBridge/<course_code>/). Can also be specified with --downloads <directory>. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| paperbridge_statusB | 检查西浦图书馆历年试卷库独立登录状态和登录进度。PaperBridge 使用独立的本人会话。 |
| paperbridge_loginA | 为本人打开试卷库专用登录窗口。本人完成学校 SSO、阅读并确认试卷使用协议，再搜索一次课程代码。立即返回，随后用 paperbridge_status 检查；不代填密码、不自动同意协议。 |
| paperbridge_searchA | 按课程代码检索本人有权访问的西浦历年试卷，返回标题、学年和 record_id。有 next_page 时继续翻页，不猜测试卷 ID。按正考/补考或学期选择前调用 paperbridge_details，不能只看同名标题。未登录先调用 paperbridge_login。 |
| paperbridge_detailsA | 读取检索得到的试卷详情，返回学年、学期和考试类型（Final 正考 / Resit 补考），一次最多 20 份。用于区分同年同名的试卷，不读取题目正文。 |
| paperbridge_downloadA | 将检索结果中选定的试卷 PDF 保存到本人电脑，按课程代码归档。record_ids 必须来自 paperbridge_search，一次最多 20 份，按顺序下载并校验 PDF；不返回 Cookie、token 或临时签名链接。 |
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 5 tools
Each tool targets a distinct step or resource: login, status, search, details, and download. Their boundaries are reinforced by cross-references (e.g. details needed before filtering, record_ids must come from search), leaving no realistic confusion.
All five tools share the same `paperbridge_` prefix followed by a short identifier (search, details, download, status, login). The suffixes mix verbs and nouns (download/search vs details/status), a minor deviation but the pattern remains predictable and readable.
Five tools map cleanly onto a search-inspect-download workflow with authentication states. Each tool earns its place with no redundancy or bloat.
The surface covers the full lifecycle: authenticating (login/status), discovering (search), disambiguating (details), and retrieving (download). No obvious gaps remain for this domain.