← 返回 Skills 市场
187
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install xiaohongshu-mcp-node-skill
功能描述
通过 MCP 协议操作小红书平台,支持内容发布、搜索、互动等完整功能
安全使用建议
This skill appears to do what it says (drive Xiaohongshu through an MCP server implemented with Node + Playwright), but you should take precautions before installing: 1) Inspect the GitHub repository and any install.sh script before running it — piping remote scripts to bash is risky. 2) Treat cookies.json as sensitive (it contains authentication). Store it with restrictive permissions (chmod 600), keep it local, and consider using a throwaway/test account. 3) Consider cloning and reviewing the code, or running the MCP server in an isolated VM/container rather than on a production machine. 4) Be aware of account‑risk: automation can trigger platform rate limits or bans. 5) If you must install, avoid curl|bash; download the repo and review scripts, then run npm install and npx playwright install chromium manually. If you want a stronger assurance, ask the author for a reproducible release (GitHub Releases tarball with checksums) or perform a security review of the repository before trusting it.
功能分析
Type: OpenClaw Skill
Name: xiaohongshu-mcp-node-skill
Version: 0.1.0
The skill bundle provides documentation and configuration for an MCP server to automate Xiaohongshu (XHS) interactions, including content publishing, searching, and account management. It requires high-risk capabilities such as shell execution (via Node.js), network access, and local file system access for managing session cookies and media uploads. While these are plausibly needed for the stated purpose, the inclusion of a 'curl | bash' installation script in quick-start.md and the handling of sensitive session data (cookies.json) meet the threshold for a suspicious classification. No evidence of intentional malice, such as data exfiltration or unauthorized remote control, was found in the provided files (SKILL.md, quick-start.md, faq.md).
能力评估
Purpose & Capability
The skill claims to provide Xiaohongshu automation via an external MCP server (xiaohongshu-mcp-node). The required runtimes (Node >=20, Playwright/Chromium) and the described CLI tools match that purpose. Minor inconsistency: metadata lists no required env vars, but the SKILL.md and examples reference environment entries (HEADLESS, COOKIES_PATH) and expect a cookies.json file for authentication.
Instruction Scope
SKILL.md instructs the user/agent to clone, npm install, build, run login flows, and run the MCP server; it also expects local file paths (images, video) and will download image URLs. The quick-start recommends piping a remote install.sh via curl | bash (raw.githubusercontent.com), which grants arbitrary remote script execution. The instructions do not ask the agent to read unrelated system credentials, but they do rely on local cookie files which are sensitive.
Install Mechanism
There is no formal install spec in the registry; installation is instruction-driven and requires cloning a GitHub repo and running npm scripts. The quick-start includes a high-risk pattern (curl -fsSL <raw.githubusercontent> | bash). Building and running third‑party code from GitHub and running its npm scripts is expected for this functionality but constitutes a supply‑chain and code‑execution risk that should be audited.
Credentials
The skill does not declare required credentials in registry metadata, but runtime usage depends on a local cookies.json (authentication) and optional env vars (COOKIES_PATH, HEADLESS). Cookies are equivalent to account credentials and must be protected; the skill's claims that cookies remain local are unverifiable from the docs alone. No unrelated cloud credentials or extra secrets are requested, which is appropriate.
Persistence & Privilege
always:false and model invocation is allowed (default). The skill runs an external MCP server process configured by the user; it does not request elevated or permanent platform privileges, nor does it claim to modify other skills or global agent settings.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install xiaohongshu-mcp-node-skill - 安装完成后,直接呼叫该 Skill 的名称或使用
/xiaohongshu-mcp-node-skill触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.0
xiaohongshu-mcp-node-skill 0.1.0 — Initial Release
- Provides a comprehensive SKILL.md with detailed usage instructions for xiaohongshu-mcp-node.
- Describes all major features: login, publishing (text/image/video), content search, interaction (comment/like/favorite), and getting recommendations.
- Lists keyword triggers for automatic workflow invocation.
- Includes step-by-step setup and troubleshooting guides.
- Clearly outlines security, input/output standards, and privacy practices.
元数据
常见问题
Xiaohongshu Mcp Node 是什么?
通过 MCP 协议操作小红书平台,支持内容发布、搜索、互动等完整功能. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 187 次。
如何安装 Xiaohongshu Mcp Node?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install xiaohongshu-mcp-node-skill」即可一键安装,无需额外配置。
Xiaohongshu Mcp Node 是免费的吗?
是的,Xiaohongshu Mcp Node 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Xiaohongshu Mcp Node 支持哪些平台?
Xiaohongshu Mcp Node 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Xiaohongshu Mcp Node?
由 PING SI(@sipingme)开发并维护,当前版本 v0.1.0。
推荐 Skills