Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"taobao-title-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# 淘宝标题生成 MCP 服务器 这是一个基于 MCP (Model Context Protocol) 协议的淘宝商品标题生成服务器,可以根据商品图片自动生成优化的淘宝商品标题。 ## 功能特点 - 支持多图片输入,提供更全面的商品分析 - 异步处理请求,支持进度报告 - 提供资源访问,包括API描述和使用指南 - 预定义提示,帮助LLM更高效地使用服务 - 完全兼容MCP协议,可与支持MCP的LLM客户端无缝集成 ## 安装 ### 从PyPI安装 ```bash pip install taobao-title-mcp ``` ### 从源码安装 ```bash git clone <repository-url> cd taobao-title-mcp pip install -e . ``` ## 使用方法 ### 作为独立服务器运行 ```bash # 如果已安装为包 python -m taobao_title_mcp # 或者使用uvx(如果已发布到PyPI) uvx taobao-title-mcp ``` ### 在代码中使用 ```python from taobao_title_mcp.server import mcp from taobao_title_mcp import tools, resources, prompts # 启动服务器 mcp.run() ``` ## 工具和资源 ### 工具 - `generate_taobao_title`: 根据商品图片URL生成淘宝商品标题 ### 资源 - `info://api_description`: API描述信息 - `info://usage_guidelines`: API使用指南 - `examples://{example_id}`: 示例数据,支持的example_id: shoes, clothes, electronics ### 提示 - `generate_title_from_images`: 根据图片URL生成标题的提示 - `analyze_title_quality`: 分析标题质量并提供改进建议的提示 ## 示例 使用MCP客户端调用服务: ```python from mcp.client import Client async def main(): async with Client("http://localhost:8000") as client: # 获取API描述 api_info = await client.read_resource("info://api_description") print(f"API名称: {api_info['name']}") # 生成标题 result = await client.call_tool( "generate_taobao_title", { "image_urls": [ "https://gw.alicdn.com/imgextra/i4/215590895/O1CN01wcB8AU1ITxVvVRZyZ_!!215590895.jpg" ], "temperature": 0.7 } ) print(f"生成的标题: {result['title']}") print(f"处理时间: {result['processing_time']}秒") ``` ## 开发 ### 依赖 - Python 3.8+ - mcp 1.6.0+ - requests - Pillow ### 测试 ```bash pytest tests/ ``` ## 许可证 MIT ## 作者 三少科技
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.