What problem it solves

AI assistants need a standard way to access Xiaohongshu data and perform publishing and interaction tasks. This project provides an HTTP MCP server that exposes Xiaohongshu operations through tools usable by MCP-compatible clients.

Key features

• Publish image and video posts — Publish image or video content with a title, description, tags, scheduling, visibility, and optional product information.

  Source: README

• Search and inspect Xiaohongshu content — Search posts by keyword, inspect recommendation feeds, and retrieve post details, interaction data, and comments.

  Source: README

• Interact with posts and comments — Post comments, reply to a specific comment, and like or favorite notes with state-aware operations that avoid repeating an action.

  Source: README

• Use the standard MCP interface — Connect the HTTP service to MCP-compatible AI clients, with optional bearer-token authentication for deployment environments.

  Source: README, mcp_server.go

• Choose flexible deployment options — Run precompiled binaries, build from Go source, or use Docker in headless or noVNC interface mode.

  Source: README

Quick start

Copied verbatim from the project's README.

# 1. 首先运行登录工具
chmod +x xiaohongshu-login-darwin-arm64
./xiaohongshu-login-darwin-arm64

# 2. 然后启动 MCP 服务
chmod +x xiaohongshu-mcp-darwin-arm64
./xiaohongshu-mcp-darwin-arm64

# 默认：无头模式，没有浏览器界面
go run .

# 非无头模式，有浏览器界面
go run . -headless=false

帮我检查小红书登录状态

Who it may suit

This may suit developers and AI-client users who want to automate Xiaohongshu workflows through MCP. It may also suit teams that need publishing, search, comment, user-profile, and interaction tools behind a standard HTTP interface.

Topics to discuss

• Which additional MCP tools would be most useful for Xiaohongshu workflows?

• How should authentication and cookie lifecycle be handled across different deployment environments?

• Which MCP client integrations should receive more complete configuration examples and tests?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/xpzouying/xiaohongshu-mcp#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.