rednote-mind-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_login_statusA | 检查小红书登录状态。返回是否已登录以及相关消息。 |
| loginA | 登录小红书。会打开浏览器窗口引导用户扫码或密码登录，登录成功后会自动保存cookies供后续使用。 |
| search_notes_by_keywordA | 按关键词搜索小红书笔记。返回搜索结果列表（包含标题、URL、封面、作者）。 |
| get_favorites_listA | 从当前登录用户的收藏夹获取笔记列表。返回笔记的基本信息（标题、URL、封面等），但不包含详细内容和图片。 |
| get_note_contentA | 获取笔记的完整内容。可选择是否包含图片和详细数据（标签、点赞、收藏、评论）。图片处理模式：original 返回压缩后的原始图片（Base64），vlm 使用 VLM 分析图片并返回文字描述（支持智增增 ZZZ_API_KEY、Jina JINA_API_KEY 或智谱 ZHIPU_API_KEY，按此优先级选择）。重要：必须使用从 get_favorites_list 或 search_notes_by_keyword 返回的带 xsec_token 参数的完整 URL，否则可能访问失败。 |
| get_batch_notes_from_favoritesA | 从当前用户收藏夹批量获取笔记的完整内容（包含文本和图片）。此工具会自动调用 get_favorites_list 获取收藏列表，然后对每条笔记调用 get_note_content 获取详细内容。所有URL会自动包含 xsec_token 参数。适用于批量分析收藏的笔记。 |
| download_note_imagesA | 下载笔记的所有图片并保存到本地 ~/.mcp/rednote/images/{noteId}/ 目录，返回文件路径列表。包括轮播图中的所有图片。图片会自动压缩以节省存储空间。重要：必须使用从 get_favorites_list 或 search_notes_by_keyword 返回的带 xsec_token 参数的完整 URL，否则可能访问失败。 |
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 has a clearly distinct purpose: login/check status, search, list favorites, get note content, batch get favorites content, download images. The composite batch tool is explicitly documented as a convenience wrapper, so no ambiguity.
All tool names follow a consistent snake_case verb_noun pattern (e.g., get_favorites_list, download_note_images, check_login_status). 'login' is a simple verb, but it is a common exception and does not break the overall consistency.
Seven tools cover the core operations of searching, reading favorites, retrieving note content, downloading images, and authentication without unnecessary bloat. The count is well within the ideal 3-15 range for a focused server.
The tool set provides a complete lifecycle for the domain: login to access, search to discover, list favorites, fetch full content, batch-process favorites, and download images. There are no obvious dead ends or missing operations needed for the stated purpose.