weread-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WEREAD_API_KEY | No | 服务端默认 API Key | |
| WEREAD_MCP_HOST | No | 监听地址 | 127.0.0.1 |
| WEREAD_MCP_PORT | No | 监听端口 | 8000 |
| WEREAD_MCP_SSE_PATH | No | SSE 路径 | /sse |
| WEREAD_MCP_HTTP_PATH | No | Streamable HTTP 路径 | /mcp |
| WEREAD_MCP_LOG_LEVEL | No | 日志级别 | INFO |
| WEREAD_MCP_TRANSPORT | No | MCP 传输方式: sse / streamable-http / stdio | sse |
| WEREAD_SKILL_VERSION | No | 上报给网关的 skill 版本 | 1.0.4 |
| WEREAD_REQUEST_TIMEOUT | No | 网关请求超时(秒) | 30 |
| WEREAD_MCP_MESSAGE_PATH | No | SSE 消息路径 | /messages/ |
| WEREAD_ALLOW_CLIENT_API_KEY | No | 是否允许请求头覆盖 Key | true |
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 |
|---|---|
| search_booksA | 在微信读书书城搜索( |
| get_book_infoA | 获取书籍基本信息( |
| get_book_chaptersA | 获取书籍章节目录( |
| get_reading_progressA | 获取某本书的阅读进度( |
| get_shelfA | 获取当前用户书架( |
| list_notebooksA | 列出所有有笔记的书( |
| get_book_highlightsA | 获取我在某本书里的划线内容( |
| get_my_reviewsA | 获取我在某本书里的个人想法与点评( |
| get_chapter_underlinesA | 获取某章节内每条划线的热度统计( |
| get_best_highlightsA | 获取书籍/章节的热门划线( |
| get_highlight_reviewsA | 获取指定划线范围下面的想法/评论( |
| get_review_detailA | 获取单条想法的完整详情( |
| get_read_statsA | 获取个人阅读统计( |
| list_book_reviewsA | 获取书籍的公开点评( |
| recommend_booksA | 基于个人阅读记录的个性化推荐( |
| similar_booksA | 基于某本书的相似推荐( |
| get_reading_overviewA | 一次性汇总用户阅读概况(对应官方 |
| list_gateway_apisA | 列出微信读书网关当前可用的全部接口及参数定义( |
| call_gatewayA | 直连网关的兜底工具:当某个接口还没有对应的专用工具时使用。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| weread-skill-index | 总纲:统一入口、鉴权、请求/响应格式与通用规则(官方 SKILL.md) |
| weread-skill-search | 搜索:scope 选择指引、关键词提取规则、回包字段与翻页 |
| weread-skill-book | 书籍信息:详情、章节目录、阅读进度(progress 口径) |
| weread-skill-shelf | 书架:books / albums / mp 的数量口径与公开私密统计 |
| weread-skill-notes | 笔记划线:统计口径与导出口径、游标分页、热门划线与想法 |
| weread-skill-readdata | 阅读统计:字段单位(秒)、周期组合、日均口径 |
| weread-skill-review | 书籍公开点评:双层嵌套结构、评分星级换算、筛选类型 |
| weread-skill-discover | 推荐发现:个性化推荐与相似书推荐的必填参数 |
| weread-skill-profile | 阅读概况:书架 + 最近进度 + 笔记的组合工作流 |
TDQS
Scored across 19 tools
Most tools map cleanly to distinct API endpoints or user workflows, but the review/highlight cluster (get_book_highlights, get_best_highlights, get_highlight_reviews, get_my_reviews, list_book_reviews, get_review_detail) creates some overlap risk. The detailed descriptions do a good job of separating them, so misselection should be rare.
The dominant get_/list_/search_ snake_case pattern is consistent and readable. Minor deviations exist—recommend_books and similar_books lack a get_/list_ prefix, and get_reading_progress vs get_read_stats uses inconsistent root wording—but these do not seriously hinder prediction.
19 tools is on the heavier side, but each one covers a meaningful facet of the WeChat Reading domain: discovery, shelf, progress, highlights, reviews, stats, and recommendations. The two gateway-level meta tools add some noise but serve a legitimate fallback purpose.
The tool surface covers the core read-only workflows well: searching books, viewing shelf/progress, exporting highlights and reviews, pulling reading statistics, and getting recommendations. Mutating actions like adding to shelf or updating progress are absent, but they are likely outside the API's scope, and call_gateway provides a raw escape hatch for missing endpoints.