Large Language Models (LLMs) increasingly rely on external tools to perform complex, realistic tasks, yet their ability to utilize the rapidly expanding Model Contextual Protocol (MCP) ecosystem remains limited. Existing MCP research covers few servers, depends on costly manual curation, and lacks training support, hindering progress toward real-world deployment. To overcome these limitations, we introduce MCP-Flow, an automated web-agent-driven pipeline for large-scale server discovery, data synthesis, and model training. MCP-Flow collects and filters data from 1166 servers and 11536 tools, producing 68733 high-quality instruction-function call pairs and 6439 trajectories, far exceeding prior work in scale and diversity. Extensive experiments demonstrate MCP-Flow's effectiveness in driving superior MCP tool selection, function-call generation, and enhanced agentic task performance. MCP-Flow thus provides a scalable foundation for advancing LLM agents' proficiency in real-world MCP environments. MCP-Flow is publicly available at \href{https://github.com/wwh0411/MCP-Flow}{https://github.com/wwh0411/MCP-Flow}.

翻译：大型语言模型（LLMs）日益依赖外部工具来执行复杂的现实任务，但其利用快速扩展的模型上下文协议（MCP）生态系统的能力仍然有限。现有的MCP研究覆盖服务器数量少，依赖成本高昂的人工标注，且缺乏训练支持，阻碍了其向现实世界部署的进程。为克服这些限制，我们提出了MCP-Flow，这是一个自动化、由网络智能体驱动的大规模服务器发现、数据合成与模型训练流程。MCP-Flow从1166个服务器和11536个工具中收集并筛选数据，生成了68733个高质量的指令-函数调用对和6439条任务轨迹，在规模和多样性上远超先前工作。大量实验证明，MCP-Flow在驱动卓越的MCP工具选择、函数调用生成以及提升智能体任务性能方面具有显著效果。因此，MCP-Flow为提升LLM智能体在现实世界MCP环境中的熟练度提供了一个可扩展的基础。MCP-Flow已在\\href{https://github.com/wwh0411/MCP-Flow}{https://github.com/wwh0411/MCP-Flow}公开提供。