Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add autoclaw-cc/xiaohongshu-mcp-skills --skill setup-xhs-mcpgit clone --depth 1 https://github.com/autoclaw-cc/xiaohongshu-mcp-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/autoclaw-cc/xiaohongshu-mcp-skills/setup-xhs-mcp)<a href="https://agentmods.dev/skills/autoclaw-cc/xiaohongshu-mcp-skills/setup-xhs-mcp"><img src="https://agentmods.dev/badge/skills/autoclaw-cc/xiaohongshu-mcp-skills/setup-xhs-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/autoclaw-cc/xiaohongshu-mcp-skills/setup-xhs-mcp"><img src="https://agentmods.dev/badge/skills/autoclaw-cc/xiaohongshu-mcp-skills/setup-xhs-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.01203 |
| Opus 5 | $0.00039 | $0.00602 |
| Sonnet 5 | $0.00015 | $0.00241 |
| Haiku 4.5 | $0.00008 | $0.00120 |
Grade B, and why
setup-xhs-mcp scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Claude Code**:读取 `~/.claude/settings.json` 和项目级 `.claude/settings.json`,查找 `mcpServers` 中是否有 `xiaohongshu` 配置。 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -so /dev/null http://localhost:18060/mcp && echo "running" || echo "not running" How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目仓库:https://github.com/xpzouying/xiaohongshu-mcp
执行流程
1. 检测服务状态
检查 xiaohongshu-mcp 是否已在运行(注意:MCP 端点只接受 POST,GET 会返回 405,不能用 -f 判断):
curl -so /dev/null http://localhost:18060/mcp && echo "running" || echo "not running"
- 已运行 → 记录地址
http://localhost:18060/mcp,跳到步骤 3 - 未运行 → 询问用户:服务是否部署在其他地址/端口?
- 用户提供地址 → 验证可达后跳到步骤 3
- 未部署 → 进入步骤 2
2. 部署服务
确认操作系统(macOS / Linux / Windows)和是否已安装 Docker。
方式一:Docker Compose(推荐)
Docker 镜像内置 Chrome 和中文字体,无需额外配置。
# 下载 docker-compose.yml
wget https://raw.githubusercontent.com/xpzouying/xiaohongshu-mcp/main/docker/docker-compose.yml
# 启动服务
docker compose up -d
# 查看日志
docker compose logs -f
镜像源:
- Docker Hub(默认):
xpzouying/xiaohongshu-mcp - 阿里云(国内推荐):
crpi-hocnvtkomt7w9v8t.cn-beijing.personal.cr.aliyuncs.com/xpzouying/xiaohongshu-mcp
切换方法:编辑 docker-compose.yml,注释默认 image 行,取消注释阿里云 image 行。
数据持久化:
./data— cookies 登录状态./images— 发布图片时的挂载目录
方式二:下载二进制
从 GitHub Releases 下载:https://github.com/xpzouying/xiaohongshu-mcp/releases/latest
curl -s https://api.github.com/repos/xpzouying/xiaohongshu-mcp/releases/latest | grep browser_download_url
注意:二进制方式需要本机已安装 Chrome 或 Chromium。
方式三:源码编译
不推荐,仅适合 Go 开发者。参考项目仓库 README。
部署完成后用 curl 确认服务已启动,然后进入步骤 3。
3. 检测 MCP 连接配置
检查当前客户端是否已配置 xiaohongshu MCP 连接。
Claude Code:读取 ~/.claude/settings.json 和项目级 .claude/settings.json,查找 mcpServers 中是否有 xiaohongshu 配置。
- 已配置且地址正确 → 跳到步骤 5
- 已配置但地址不匹配 → 修正地址
- 未配置 → 进入步骤 4
4. 配置 MCP 连接
询问用户:
连接地址:如果步骤 1 已确认可达的地址,用该地址作为默认值,否则默认 http://localhost:18060/mcp。
使用的客户端:
Claude Code:
claude mcp add xiaohongshu --transport http <地址>
或写入配置文件:
- 全局:
~/.claude/settings.json - 项目级:
.claude/settings.json
{
"mcpServers": {
"xiaohongshu": {
"url": "http://localhost:18060/mcp"
}
}
}
Cursor(.cursor/mcp.json):
{
"mcpServers": {
"xiaohongshu": {
"url": "http://localhost:18060/mcp"
}
}
}
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 144 lines · 77 tokens per session scan B f0b81b210092
setup-xhs-mcp is a skill published in the GitHub repository autoclaw-cc/xiaohongshu-mcp-skills (257 stars, last pushed 6mo ago), licensed MIT. It adds 77 tokens to every session and 1,203 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…