douban-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DOUBAN_COOKIE | No | 登录态cookie(可选,但详情页需要) | |
| DOUBAN_LOG_LEVEL | No | 日志级别:debug/info/warn/error | info |
| DOUBAN_USER_AGENT | No | 覆盖默认UA | 内置Chrome UA |
| DOUBAN_DATA_SOURCE | No | 数据源:html或frodo | html |
| DOUBAN_ENABLE_WRITE | No | 启用写操作 | false |
| DOUBAN_FRODO_APIKEY | No | 覆盖frodo apikey | 内置默认 |
| DOUBAN_DISABLE_CACHE | No | 关闭缓存(测试用) | false |
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 |
|---|---|
| search_movieA | 按关键词搜索豆瓣电影。返回标题/年份/评分/链接的 markdown 列表。 |
| get_movieA | 获取一部电影的详细信息(导演、演员、评分、简介等)。id 是豆瓣电影 subject id(数字)。 |
| get_movie_reviewsB | 获取一部电影的短评列表(不含长评)。 |
| get_movie_chartB | 获取电影榜单。kind: top250 (Top250)、weekly (一周口碑榜)、new (近期上映)。 |
| search_bookB | 按关键词搜索豆瓣图书。 |
| get_bookA | 获取图书详情(作者、出版、ISBN、简介等)。id 是豆瓣图书 subject id(数字)。 |
| get_book_reviewsC | 获取图书的短评列表。 |
| get_book_chartC | 获取图书榜单。kind: fiction (小说)、non_fiction (随笔)、new (新书速递)。 |
| get_user_collectionsB | 获取某用户的"想看/在看/看过"列表。无 cookie 时必须传 uid。 |
| get_user_doulistA | 获取某用户的豆列清单。无 cookie 时必须传 uid。 |
| get_user_profileB | 获取某用户的基本信息。无 cookie 时必须传 uid。 |
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 11 tools
Tools split cleanly along two axes: resource (movie/book/user) and action (search/get/reviews/chart/collections/doulist/profile). The movie and book families are perfectly parallel, so an agent can pick the right tool from the name plus the kind parameter alone. No two tools overlap in scope.
Every tool follows a strict snake_case verb_noun pattern (search_movie, get_movie_reviews, get_user_doulist). Resource-first grouping (movie_*/book_*/user_*) makes the families obvious. No mixed conventions or vague verbs.
11 tools is squarely in the sweet spot, and each one earns its place: four per media type plus three user tools. The symmetric design means no filler tools and no obvious redundancy.
Read coverage is solid for movies, books, and user lists, including charts and short reviews. Gaps remain: no write operations (marking watched/want-to-watch), no long-review retrieval, no user search, and no music/media coverage despite the broad 'douban' name.