mcpField
B
blbl147-xhs-mcp

blbl147-xhs-mcp

Remote
github.com/blbl147Social Media0Updated 74w ago
Repository

About blbl147-xhs-mcp

An MCP server for interacting with Xiaohongshu notes and comments. It searches notes, retrieves their content and comments, and can publish comments; requests use reversed JavaScript signatures rather than Playwright.

Key features

  1. 01Search Xiaohongshu notes
  2. 02Retrieve note content
  3. 03Retrieve note comments
  4. 04Post comments
  5. 05Direct HTTP requests with JS signatures

Use cases

  1. 01Finding notes about a topic
  2. 02Reviewing a note and its comments
  3. 03Posting a comment on a note

MCP support

Exposes Xiaohongshu note search, retrieval, and comment-posting capabilities to MCP clients. The README requires an authenticated Xiaohongshu cookie.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://server.smithery.ai/@blbl147/xhs-mcp/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://server.smithery.ai/@blbl147/xhs-mcp/mcpAuth required

Tools

Details

From the project README

小红书MCP服务

smithery badge

特点

  • 采用js逆向出x-s,x-t,直接请求http接口,无须笨重的playwright
  • 搜索笔记
  • 获取笔记内容
  • 获取笔记的评论
  • 发表评论

特性

快速开始

1. 环境
  • node
  • python 3.12
  • uv (pip install uv)
2. 安装依赖

git clone [email protected]:jobsonlook/xhs-mcp.git

cd xhs-mcp
uv sync
3. 获取小红书的cookie

打开web小红书 登录后，获取cookie，将cookie配置到第4步的 XHS_COOKIE 环境变量中 cookie

4. 配置mcp server
{
    "mcpServers": {
        "xhs-mcp": {
            "command": "uv",
            "args": [
                "--directory",
                "/Users/xxx/xhs-mcp",
                "run",
                "main.py"
            ],
            "env": {
                "XHS_COOKIE": "xxxx"
            }
        }
    }
}

免责声明

本项目仅用于学习交流，禁止用于其他用途，任何涉及商业盈利目的均不得使用，否则风险自负。

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.