This MCP server allows users to interact with the Xiaohongshu platform by searching notes, retrieving note content, and managing comments without the need for heavy tools like Playwright.
From the registry: 搜索笔记、浏览首页推荐、查看笔记内容与评论,并发表你的评论。直接在工作流中与小红书内容互动,高效跟进话题。

$ git clone https://github.com/jobsonlook/xhs-mcp && cd xhs-mcp && uv synchttps://github.com/jobsonlook/xhs-mcpPlease install the `blbl147-xhs-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Clone and uv sync** — git clone https://github.com/jobsonlook/xhs-mcp, then uv sync. Python 3.12 and Node.js required. Run: `git clone https://github.com/jobsonlook/xhs-mcp && cd xhs-mcp && uv sync` (https://github.com/jobsonlook/xhs-mcp)
- **Xiaohongshu cookie** — Log in at xiaohongshu.com/explore in a browser and copy your session cookie into XHS_COOKIE. (https://www.xiaohongshu.com/explore)
Canonical MCP server config (stdio transport):
- command: `uv`
- args: ["--directory","<path-to-xhs-mcp>","run","main.py"]
- required environment variables:
- `XHS_COOKIE`: Logged-in xiaohongshu.com session cookie (example: `<your-xhs-cookie>`)
Note: Xiaohongshu (小红书) MCP server — uses JS-reversed x-s/x-t signing to hit the HTTP API directly.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.XHS_COOKIErequiredCookie required for authentication with the Xiaohongshu platform.Lightweight DMARC parser: auto-fetch email reports, visualize compliance in a single all-in-one app