Claim this agent
agentCLAWHUBUnverified

小红书

小红书自动化运营工具-支持:搜索笔记、查看笔记详情及评论、浏览推荐流、发布图文笔记。 当用户提及 xiaohongshu、小红书、RedNote,或需要在该平台进行内容调研/发布时使用。 Skill: 小红书 Owner: wscats Summary: 小红书自动化运营工具-支持:搜索笔记、查看笔记详情及评论、浏览推荐流、发布图文笔记。 当用户提及 xiaohongshu、小红书、RedNote,或需要在该平台进行内容调研/发布时使用。 Tags: latest:1.0.10 Version history: v1.0.10 | 2026-05-02T07:11:03.669Z | auto Version 1.0.10 - 增强客户端安全措施:新增自动检测,默认拒绝所有不安全或未授权的 publish 操作。 - SKILL.md 文档重写,明确所有客户端内置护栏,以及上游组件独立、非本仓库维护的提醒。 - 快速参考与市场调研、内容发布流程重构,突出强制逐步授权和机械性安全检查细节。 - 简化注意事项,删除/合并部分重复的人工安全警告,统一以客户端强制规约为准。 v1.0.7 | 2026-05-02T06:

OpenClaw

Rank

62

Safety

84

Downloads

7.6k

Updated

Oct 9, 2026

Version

1.0.10

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 7.6K downloads reported by the source. Last updated 10/9/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor
Clawhubvendor · observed Oct 9, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 9, 2026
Adoption signal
7.6K downloadsadoption · observed Oct 9, 2026
Latest release
1.0.10release · observed May 2, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17bw1sf2hsjw09jmyh7nhzshn83h2gf:xhs-cn
  1. Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-wscats-xhs-cn/snapshot"

Documentation

CLAWHUB

80,038 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: xiaohongshu
description: >
  小红书自动化运营工具-支持:搜索笔记、查看笔记详情及评论、浏览推荐流、发布图文笔记。
  当用户提及 xiaohongshu、小红书、RedNote,或需要在该平台进行内容调研/发布时使用。
---

# 小红书 MCP

本 Skill 是一个薄的 Python 客户端,通过 HTTP 调用用户**自行独立安装、启动并保管**的第三方本地组件 [xpzouying/xiaohongshu-mcp](https://github.com/xpzouying/xiaohongshu-mcp)。本 Skill 不分发、不捆绑、不自动拉取任何第三方二进制。首次安装请参阅 [SETUP.md](SETUP.md)。

## 客户端侧自动护栏(客户端拒绝执行的条件)

以下检查由 `scripts/xhs_client.py` **自动执行**,任何一项不满足都会直接拒绝发起调用:

| 检查 | 触发条件 | 客户端行为 |
| ---- | -------- | ---------- |
| Loopback 端点 | 目标地址不解析到 127.0.0.1/localhost/::1 | 进程启动即拒绝(退出码 1) |
| 非交互发布 | stdin 非 TTY 且未传 `--yes` | 拒绝 `publish`,返回 error |
| 交互发布确认 | TTY 下用户未输入 `PUBLISH` 字面量 | 取消 `publish` |
| 专用账号声明 | `XHS_DEDICATED_ACCOUNT` 未显式置 `yes` | 拒绝 `publish` |
| 上游版本可见性 | `XHS_UPSTREAM_PINNED_VERSION` 未设置 | `status` 输出中性提醒 |

这些不是建议,是**运行时机械拒绝**。用户或代理无需依赖额外自律。

## 快速参考

```bash
python scripts/xhs_client.py status
python scripts/xhs_client.py search "美食推荐"
python scripts/xhs_client.py search "美食" --sort "最多点赞" --type "图文" --time "一周内"
python scripts/xhs_client.py detail <feed_id> <xsec_token> --comments
python scripts/xhs_client.py feeds
python scripts/xhs_client.py publish "标题" "正文" "图1,图2" --tags "标签1,标签2"
```

所有命令支持 `--json` 输出原始 JSON。

## 工作流:市场调研(只读)

```
进度:
- [ ] 第 1 步:验证连接
- [ ] 第 2 步:搜索关键词
- [ ] 第 3 步:获取笔记详情
- [ ] 第 4 步:分析结果
```

**第 1 步**

```bash
python scripts/xhs_client.py status
```

**第 2 步**

```bash
python scripts/xhs_client.py search "户外电源" --sort "最多点赞" --json
```

筛选:`--sort`(综合/最新/最多点赞/最多评论/最多收藏)、`--type`(不限/视频/图文)、`--time`(不限/一天内/一周内/半年内)。

**第 3 步**

```bash
python scripts/xhs_client.py detail "<feed_id>" "<xsec_token>" --comments --json
```

**第 4 步**

查看笔记内容、互动数据(点赞、收藏、评论)与评论情感倾向。

## 工作流:发布内容

```
进度:
- [ ] 第 1 步:验证连接
- [ ] 第 2 步:准备素材
- [ ] 第 3 步:向用户展示预览并获取逐次授权
- [ ] 第 4 步:发起发布(受客户端护栏保护)
- [ ] 第 5 步:验证上线
```

**第 1 步**

```bash
python scripts/xhs_client.py status
```

**第 2 步**

准备标题(建议 ≤ 20 字)、正文、可公开访问的图片 URL、可选标签。

**第 3 步 — 代理必须执行的强制预览**

调用 `publish` 前,代理必须向用户打印结构化预览并等待用户在对话中回复明确授权词:

```
📋 发布预览
────────────
账号:<status 返回的账号>
标题:<title>
正文:<content 全文>
图片:<逐行 URL>
标签:<tags>
────────────
请回复“确认发布”以继续;任何其他回复视为取消。
```

模糊回复、沉默、或"以后都可以发"等概括授权**一律视为未授权**。

**第 4 步 — 发起发布**

仅在收到用户授权后执行:

```bash
python scripts/xhs_client.py publish "标题" "正文" "https://img1.jpg,https://img2.jpg" --tags "标签1,标签2"
```

客户端会再对第 3 步的授权做机械验证(TTY 二次确认或 `--yes` + 专用账号声明)。

**第 5 步**

```bash
python scripts/xhs_client.py search "标题" --sort "最新"
```

## 注意事项

- **频率控制**:请适当控制请求间隔。
- **维护脚本**:`scripts/publish.sh` 仅用于把本 Skill 包发布到 ClawHub 市场,与"在小红书发布笔记"无关,终端用户无需运行。

_meta.json

{
  "ownerId": "kn78mv1912530wvdbf2vjcd3r982v66j",
  "slug": "xhs-cn",
  "version": "1.0.10",
  "publishedAt": 1777705863669
}

SETUP.md

# 服务器安装(仅首次需要)

本 Skill 的运行依赖一个**独立的第三方本地组件** [xpzouying/xiaohongshu-mcp](https://github.com/xpzouying/xiaohongshu-mcp)。本 Skill 自身**不包含、不分发、不打包**该组件的任何二进制或源代码,也**不会自动下载**它。是否安装、安装哪个版本、授予哪种账号权限,**完全由用户本人在安装本 Skill 之前独立决定**。

## 安装前检查清单(Preflight Checklist)

在继续之前,请逐项勾选以下条件。**如有任何一项无法满足,请停止安装本 Skill**:

- [ ] 我已独立审核并信任第三方组件 `xpzouying/xiaohongshu-mcp`。
- [ ] 我会使用一个**独立注册的专用账号**,不会使用我的主账号或企业账号。
- [ ] 我会将该组件仅运行在受我本人物理控制的个人电脑上。
- [ ] 我会使用该组件的默认 loopback 配置,不会修改其网络绑定。
- [ ] 我理解并接受:该组件运行期间可代表上述专用账号发布公开内容,误操作不可撤回。
- [ ] 任务完成后,我会停止该组件进程,并在官方 App 中手动吊销对应的登录设备。

> ℹ️ 本 Skill 随附的 Python 客户端 `scripts/xhs_client.py` 在客户端一侧已内置多道自动拒绝机制:
> 非 loopback 端点、非交互环境下的发布、未声明专用账号的发布,都会被**直接拒绝执行**,
> 详见 `xhs_client.py` 顶部注释。

## 第 0 步:安装 Python 依赖

```bash
pip install requests
```

## 第 1 步:获取第三方 MCP 组件(推荐从源码编译)

为避免供应链风险,**推荐**直接从官方仓库克隆并锁定到一个你已审核的具体版本 tag,然后用 Go 工具链自行编译:

```bash
git clone https://github.com/xpzouying/xiaohongshu-mcp.git
cd xiaohongshu-mcp
git checkout <YOUR_REVIEWED_TAG>     # 必须是一个你已人工审核过的具体 tag,禁止使用 main/latest
go build -o xiaohongshu-mcp ./cmd/mcp
go build -o xiaohongshu-login ./cmd/login
```

如必须使用预编译产物,请从 [官方 Releases](https://github.com/xpzouying/xiaohongshu-mcp/releases) 下载指定 tag 的文件,并核对其 SHA256 与你从源码独立计算的哈希一致后再使用。

完成后,将你确认使用的版本号写入环境变量,供本 Skill 的客户端进行一致性提示:

```bash
export XHS_UPSTREAM_PINNED_VERSION="<YOUR_REVIEWED_TAG>"
```

## 第 2 步:登录

完成登录后,客户端会声明你正在使用的是**专用账号**;本 Skill 的 `publish` 命令要求用户显式设置该声明后才会放行:

```bash
export XHS_DEDICATED_ACCOUNT=yes     # 只有在你用的是独立的专用账号时才设置
./xiaohongshu-login-<your-platform>  # 扫码登录
```

## 第 3 步:启动 MCP 组件(保持默认 loopback 绑定)

按照第三方组件文档的**默认**方式启动即可(其默认就绑定在本机回环接口)。本 Skill 的客户端会验证端点必须是 loopback,否则**直接拒绝发起任何请求**。

```bash
./xiaohongshu-mcp-<your-platform>
```

## 第 4 步:验证

```bash
python scripts/xhs_client.py status
```

## 使用结束后

```bash
pkill -f xiaohongshu-mcp
unset XHS_DEDICATED_ACCOUNT XHS_UPSTREAM_PINNED_VERSION
```

并在小红书官方 App 的「登录设备管理」中主动下线对应设备。

skill-card.md

## Description:

小红书 helps agents search Xiaohongshu notes, inspect details and comments, browse recommended feeds, and publish image-text posts through a user-managed local MCP component.

This skill is ready for commercial/non-commercial use.

## Publisher:

[wscats](https://clawhub.ai/user/wscats)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, creators, and operators use this skill to research Xiaohongshu content, review note details and comments, browse feeds, and prepare authorized image-text posts. Publishing requires a user-managed local MCP service and explicit per-post authorization.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: A non-local MCP endpoint override could send Xiaohongshu tokens or draft post content to a remote server.

Mitigation: Keep the endpoint on loopback by default, and do not set XHS_ALLOW_REMOTE=yes or XHS_MCP_BASE_URL to a non-loopback address unless the server is fully trusted.

Risk: The required third-party local MCP component can act through the configured Xiaohongshu account, including publishing public content.

Mitigation: Audit and pin the upstream component version, use a dedicated Xiaohongshu account, review each post before publishing, stop the component after use, and revoke the login device in the official app.

Risk: The maintainer publish script is unrelated to end-user Xiaohongshu posting and mutates ClawHub distribution state.

Mitigation: Normal users should not run scripts/publish.sh; reserve it for maintainers with the required ClawHub credentials and explicit publish confirmation.

## Reference(s):

- [ClawHub Skill Page](https://clawhub.ai/wscats/skills/xhs-cn)
- [SETUP.md](SETUP.md)
- [xpzouying/xiaohongshu-mcp](https://github.com/xpzouying/xiaohongshu-mcp)
- [xiaohongshu-mcp Releases](https://github.com/xpzouying/xiaohongshu-mcp/releases)

## Skill Output:

**Output Type(s):** [Text, Markdown, JSON, Shell commands, Guidance]

**Output Format:** [Markdown guidance with shell commands and optional JSON command output]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Commands interact with a user-managed local MCP service; publish operations require explicit authorization and a dedicated-account attestation.]

## Skill Version(s):

1.0.10 (source: server release evidence, released 2026-05-02)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/wscats/skills/xhs-cn",
      "sourceUrl": "https://clawhub.ai/wscats/skills/xhs-cn",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T02:53:12.763Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-wscats-xhs-cn/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-wscats-xhs-cn/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-09T02:53:12.763Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "7.6K downloads",
      "href": "https://clawhub.ai/wscats/xhs-cn",
      "sourceUrl": "https://clawhub.ai/wscats/xhs-cn",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-09T02:53:12.763Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.0.10",
      "href": "https://clawhub.ai/wscats/xhs-cn",
      "sourceUrl": "https://clawhub.ai/wscats/xhs-cn",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-02T07:11:03.669Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-wscats-xhs-cn/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-wscats-xhs-cn/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.0.10",
      "description": "Version 1.0.10 - 增强客户端安全措施:新增自动检测,默认拒绝所有不安全或未授权的 `publish` 操作。 - SKILL.md 文档重写,明确所有客户端内置护栏,以及上游组件独立、非本仓库维护的提醒。 - 快速参考与市场调研、内容发布流程重构,突出强制逐步授权和机械性安全检查细节。 - 简化注意事项,删除/合并部分重复的人工安全警告,统一以客户端强制规约为准。",
      "href": "https://clawhub.ai/wscats/xhs-cn",
      "sourceUrl": "https://clawhub.ai/wscats/xhs-cn",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-05-02T07:11:03.669Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 9, 2026.

Sponsored

Ads related to 小红书 and adjacent AI workflows.