{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_gd7nt2gng5gw","handle":"yooztech-mcp-taobao-search","url":"https://wellknown.network/agents/yooztech-mcp-taobao-search","links":{"self":"https://wellknown.network/agents/yooztech-mcp-taobao-search/record.json","html":"https://wellknown.network/agents/yooztech-mcp-taobao-search","markdown":"https://wellknown.network/agents/yooztech-mcp-taobao-search/record.md","api":"https://wellknown.network/api/v1/agents/yooztech-mcp-taobao-search","status":"https://wellknown.network/api/v1/agents/yooztech-mcp-taobao-search/status","claim":"https://wellknown.network/agents/yooztech-mcp-taobao-search/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/yooztech-mcp-taobao-search/claim.json","badge":"https://wellknown.network/agents/yooztech-mcp-taobao-search/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/yooztech-mcp-taobao-search/history","tools":"https://wellknown.network/api/v1/agents/yooztech-mcp-taobao-search/tools"},"ard":{"identifier":"urn:air::server:yooztech-mcp-taobao-search","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"yooztech-mcp-taobao-search","summary":"MCP server for Taobao search and data scraping","description":"# yooztech_mcp_taobao_search —— 淘宝搜索采集 MCP 工具\n\n基于 MCP (Model Context Protocol) 的淘宝搜索和商品数据采集工具，自动搜索关键词、提取商品信息并导出为 CSV。\n\n## 功能概述\n\n- `taobao_search(keyword, ...)`: 搜索淘宝关键词，采集商品数据并导出 CSV\n\n## 在 Cursor 中配置\n\n```json\n{\n  \"mcpServers\": {\n    \"yooztech_mcp_taobao_search\": {\n      \"command\": \"yooztech_mcp_taobao_search\",\n      \"args\": []\n    }\n  }\n}\n```\n\n或使用 `uvx` 方式：\n\n```json\n{\n  \"mcpServers\": {\n    \"yooztech_mcp_taobao_search\": {\n      \"command\": \"uvx\",\n      \"args\": [\"yooztech_mcp_taobao_search\"]\n    }\n  }\n}\n```\n\n## 工具详解\n\n### taobao_search - 淘宝搜索采集\n\n根据关键词搜索淘宝商品，自动采集商品信息并导出为 CSV 文件。\n\n**参数：**\n- `keyword` (必填): 搜索关键词\n- `max_items` (可选): 最大采集数量，默认 50，范围 1-200\n- `slowly` (可选): 是否慢速操作（推荐），默认 true，避免操作过快\n- `output_csv` (可选): CSV 输出路径，默认 `./tmp/taobao_<keyword>_<timestamp>.csv`\n- `cdp_endpoint` (可选): Chrome CDP 端点（如 `ws://127.0.0.1:9222`），如果提供则连接到已运行的 Chrome，否则启动新浏览器\n\n**返回：**\n- `success`: 是否成功\n- `csv_path`: CSV 文件路径\n- `total_collected`: 采集到的商品数量\n- `items`: 商品数据列表（前 10 条预览）\n- `notes`: 提取说明（如有）\n\n**CSV 列：**\n- 排位: 商品排名（1-based）\n- 标题: 商品标题\n- 付款人数: 付款/收货人数\n- 链接: 商品详情页链接\n- 店铺名: 店铺名称\n\n**使用示例：**\n\n```json\n{\n  \"tool\": \"taobao_search\",\n  \"args\": {\n    \"keyword\": \"iPhone 15\",\n    \"max_items\": 30,\n    \"slowly\": true\n  }\n}\n```\n\n## 工作原理\n\n1. **打开浏览器**: 使用 Playwright 通过 Chrome DevTools Protocol (CDP) 控制浏览器\n   - 可以连接到已运行的 Chrome（通过 `cdp_endpoint` 参数）\n   - 或启动新的 headed 浏览器（可见模式）\n2. **检测登录**: 访问淘宝首页，检测是否已登录\n3. **等待登录**: 如果未登录，提示用户手动登录，等待最多 5 分钟\n4. **直接导航**: 构造并导航到搜索结果 URL `https://s.taobao.com/search?page=1&q=<keyword>&tab=all`（不操作搜索框）\n5. **采集数据**: 滚动页面加载更多商品，使用 JavaScript 在页面内提取商品信息\n6. **去重导出**: 根据商品链接去重，导出为 CSV（UTF-8 BOM，Excel 兼容）\n\n## 注意事项\n\n- **浏览器要求**: 需要 Chrome/Chromium 浏览器\n- **首次使用**: 首次运行需要安装浏览器驱动：`playwright install chromium`\n- **登录检测**: 工具会自动检测登录状态，未登录时会等待用户手动登录\n- **CDP 连接**: 如果 OpenClaw 或其他工具已启动 Chrome，可通过 `cdp_endpoint` 参数连接（如 `ws://127.0.0.1:9222`）\n- **页面结构**: 淘宝页面可能 A/B 测试或更新，如果解析失败，可能需要调整选择器\n- **慢速模式**: 建议设置 `slowly=true` 避免操作过快被限制\n\n## 依赖\n\n- Python >= 3.10\n- mcp >= 1.2.0\n- playwright >= 1…","publisher":{"name":"yooztech","url":null},"homepage":null,"repository":null,"version":"0.0.1","license":"MIT","protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:yooztech-mcp-taobao-search","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"infra.browser-automation","name":"Browser Automation","confidence":0.825,"provenance":"derived"},{"slug":"documents.spreadsheets","name":"Spreadsheets","confidence":0.733,"provenance":"derived"}],"categories":["documents","infra"],"language":"en"},"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":"yooztech-mcp-taobao-search","registry":"pypi","observedAt":"2026-11-10T07:23:36.424Z","publishedAt":"2026-03-20T04:44:29.819096Z","latestVersion":"0.0.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"yooztech-mcp-taobao-search","url":"https://pypi.org/project/yooztech-mcp-taobao-search/","firstSeenAt":"2026-09-10T16:23:24.724Z","fetchedAt":"2026-11-10T07:22:37.144Z","normalizedAt":"2026-11-10T07:22:37.144Z"}]},"firstSeenAt":"2026-09-10T16:23:24.724Z","updatedAt":"2026-11-10T07:23:36.424Z"}