coweread
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| COWEREAD_HOME | No | Root directory for state/ and cache/. Defaults to the project directory. | |
| COWEREAD_SIGN | No | Prefix for AI annotations. Default is '🌕'. Leave empty to disable signature. | 🌕 |
| WEREAD_API_KEY | Yes | Official Agent API Key, starts with wrk-. Required for query and service layer functionality. | |
| COWEREAD_API_TOKEN | No | Optional token for REST/HTTP MCP. Strongly recommended when exposing the server. Requests require Authorization: Bearer <token>. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_shelfB | 书架列表（官方通道）。 |
| get_tocB | 书籍章节目录：[{chapterIdx, chapterUid, title, ...}]。写想法/读书都要用这里的 chapterUid。 |
| get_progressA | 用户真实阅读进度（只读；AI 共读进度用 get_reader_bookmark，两者严格分开）。 |
| get_chapter_textA | 章节明文 + co 索引（缓存优先；refresh=True 强制重抓）。共读前先读这个。 |
| add_reviewA | 写想法：abstract 必须逐字摘自该章原文（自动算 range，匹配失败拒绝写入）； content 前会自动加 🌕 署名。章节级想法用 add_chapter_review。 |
| add_chapter_reviewB | 章节级想法（挂在整章上，无原文引用），content 前自动加 🌕 署名。 |
| my_reviewsA | 自己在此书的全部想法（写前防重复、延续语气）。 |
| best_bookmarksC | 热门划线（选句素材；chapter_uid=0 查全书）。 |
| list_commentsA | 某条想法下的评论列表（评论 ID 形如 {reviewId}_c{...}，回复评论时用它）。 |
| add_commentA | 在想法下发评论，content 前自动加 🌕 署名。 reply_comment_id 非空即"回复某条评论"（引用模式；微信读书评论无嵌套楼层）。 |
| add_bookmarkA | 划线：abstract 必须逐字摘自该章原文（自动算 range，匹配失败拒绝划线）。 colorStyle: 1红 2紫 3蓝 4绿 5黄；style: 0直线 1荧光笔 2波浪（3 无效）。默认 5+2 黄波浪。 返回 bookmarkId，改样式/删除时用它。 |
| update_bookmark_styleA | 改已有划线的样式（bookmarkId 来自 add_bookmark 的返回）。 只传想改的字段：colorStyle: 1红 2紫 3蓝 4绿 5黄；style: 0直线 1荧光笔 2波浪（3 无效）。 |
| remove_bookmarkC | 删除划线。 |
| get_reader_bookmarkA | AI 共读伙伴自己的进度（本地，与微信读书真实进度无关）；不带参返回全部书目。 |
| set_reader_bookmarkA | 记录 AI 共读伙伴读到哪一章（共读进度；不影响用户真实进度）。 |
| reading_contextB | 便捷打包：真实进度 + 共读书签 + 章节明文 + 该章已有想法 + 热门划线。 仅作便捷工具，绝不作为读书的默认上下文——上下文组织归调用方/前端关注。 |
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 16 tools
Most tools map cleanly to distinct resources and actions, and descriptions explicitly separate user progress from AI progress and quote-based reviews from chapter-level reviews. Minor ambiguity remains because 'bookmark' is used for both highlights and reading progress, and reading_context overlaps somewhat with get_chapter_text.
The majority of tools follow a consistent verb_noun pattern like get_*, add_*, list_*, update_*, and remove_*. A few noun-phrase names such as my_reviews, best_bookmarks, and reading_context deviate, and 'bookmark' means two different things across tools.
At 16 tools, the server is slightly over the ideal 3-15 range, but each tool appears to serve a distinct purpose in the reading, review, highlight, and comment workflows. No tools feel redundant, so the count is reasonable for the scope.
The core workflows for reading, writing thoughts, commenting, highlighting, and tracking progress are covered. However, there are notable gaps: no update/delete for reviews or comments, no listing of the user's own highlights, and no book-level metadata tool beyond the shelf list.