{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_f5v693nujhcf","handle":"iflow-mcp-redbook-search-comment-mcp","url":"https://wellknown.network/agents/iflow-mcp-redbook-search-comment-mcp","links":{"self":"https://wellknown.network/agents/iflow-mcp-redbook-search-comment-mcp/record.json","html":"https://wellknown.network/agents/iflow-mcp-redbook-search-comment-mcp","markdown":"https://wellknown.network/agents/iflow-mcp-redbook-search-comment-mcp/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-redbook-search-comment-mcp","status":"https://wellknown.network/api/v1/agents/iflow-mcp-redbook-search-comment-mcp/status","claim":"https://wellknown.network/agents/iflow-mcp-redbook-search-comment-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-redbook-search-comment-mcp/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-redbook-search-comment-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-redbook-search-comment-mcp/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-redbook-search-comment-mcp/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-redbook-search-comment-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_redbook-search-comment-mcp","summary":"小红书自动搜索评论工具（MCP Server 2.0）","description":"# 小红书自动搜索评论工具（MCP Server 2.0）\n\n<div align=\"right\">\n\n[English](README_EN.md) | 中文\n\n</div>\n\n> 本项目基于 [JonaFly/RednoteMCP](https://github.com/JonaFly/RednoteMCP.git) 并结合多次实战经验，进行全面优化和功能扩展（by windsurf）。在此向原作者的贡献表示由衷的感谢！\n\n这是一款基于 Playwright 开发的小红书自动搜索和评论工具，作为 MCP Server，可通过特定配置接入 MCP Client（如Claude for Desktop），帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布AI生成评论等操作。\n\n## 主要特点与优势\n\n- **深度集成AI能力**：利用MCP客户端（如Claude）的大模型能力，生成更自然、更相关的评论内容\n- **模块化设计**：将功能分为笔记分析、评论生成和评论发布三个独立模块，提高代码可维护性\n- **强大的内容获取能力**：集成多种获取笔记内容的方法，确保能完整获取各类笔记的标题、作者和正文内容\n- **持久化登录**：使用持久化浏览器上下文，首次登录后无需重复登录\n- **两步式评论流程**：先获取笔记分析结果，然后由MCP客户端生成并发布评论\n\n## 2.0版本主要优化\n\n- **内容获取增强**：重构了笔记内容获取模块，增加页面加载等待时间和滚动操作，实现四种不同的内容获取方法\n- **AI评论生成**：重构评论功能，将笔记分析结果返回给MCP客户端，由客户端的AI能力生成更自然、更相关的评论\n- **功能模块化**：将功能分为笔记分析、评论生成和评论发布三个独立模块，提高代码可维护性\n- **搜索结果优化**：解决了搜索笔记时标题不显示的问题，提供更完整的搜索结果\n- **错误处理增强**：添加更详细的错误处理和调试信息输出\n\n## 一、核心功能\n\n### 1. 用户认证与登录\n- **持久化登录**：支持手动扫码登录，首次登录后保存状态，后续使用无需重复扫码\n- **登录状态管理**：自动检测登录状态，并在需要时提示用户登录\n\n### 2. 内容发现与获取\n- **智能关键词搜索**：支持多关键词搜索，可指定返回结果数量，并提供完整的笔记信息\n- **多维度内容获取**：集成四种不同的获取方法，确保能准确获取笔记的标题、作者、发布时间和正文内容\n- **评论数据获取**：支持获取笔记的评论内容，包括评论者、评论文本和时间信息\n\n### 3. 内容分析与生成\n- **笔记内容分析**：自动分析笔记内容，提取关键信息并识别笔记所属领域\n- **AI评论生成**：利用MCP客户端（如Claude）的AI能力，基于笔记内容生成自然、相关的评论\n- **多类型评论支持**：支持四种不同类型的评论生成：\n  - **引流型**：引导用户关注或私聊\n  - **点赞型**：简单互动获取好感\n  - **咨询型**：以问题形式增加互动\n  - **专业型**：展示专业知识建立权威\n\n### 4. 数据返回与反馈\n- **结构化数据返回**：将笔记分析结果以JSON格式返回给MCP客户端，便于AI生成评论\n- **评论发布反馈**：提供评论发布结果的实时反馈\n\n## 二、安装步骤\n\n1. **Python 环境准备**：确保系统已安装 Python 3.8 或更高版本。若未安装，可从 Python 官方网站下载并安装。\n\n2. **项目获取**：将本项目克隆或下载到本地。\n\n3. **创建虚拟环境**：在项目目录下创建并激活虚拟环境（推荐）：\n   ```bash\n   # 创建虚拟环境\n   python3 -m venv venv\n   \n   # 激活虚拟环境\n   # Windows\n   venv\\Scripts\\activate\n   # macOS/Linux\n   source venv/bin/activate\n   ```\n\n4. **安装依赖**：在激活的虚拟环境中安装所需依赖：\n   ```bash\n   pip install -r requirements.txt\n   pip install fastmcp\n   ```\n\n5. **安装浏览器**：安装Playwright所需的浏览器：\n   ```bash\n   playwright install\n   ```\n\n## 三、MCP Server 配置\n\n在 MCP Client（如Claude for Desktop）的配置文件中添加以下内容，将本工具配置为 MCP Server：\n\n### Mac 配置示例\n\n```json\n{\n …","publisher":{"name":"chenningling","url":null},"homepage":"https://github.com/iflow-mcp/Redbook-Search-Comment-MCP2.0","repository":"https://github.com/iflow-mcp/Redbook-Search-Comment-MCP2.0","version":"2.0.1","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_redbook-search-comment-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["dev"],"language":"zh"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_redbook-search-comment-mcp","registry":"pypi","observedAt":"2026-09-15T20:21:12.349Z","publishedAt":"2025-09-05T06:40:34.408895Z","latestVersion":"2.0.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_redbook-search-comment-mcp","url":"https://pypi.org/project/iflow-mcp_redbook-search-comment-mcp/","firstSeenAt":"2026-09-09T20:25:28.272Z","fetchedAt":"2026-09-15T20:18:55.853Z","normalizedAt":"2026-09-15T20:18:55.853Z"}]},"firstSeenAt":"2026-09-09T20:25:28.272Z","updatedAt":"2026-09-15T20:21:12.349Z"}