Don’t inject untrusted user input in LLM prompts. Instead, write untrusted data to a file, then instruct the LLM to read it.
CLIHub showed the path: give the LLM a CLI instead of raw tool schemas, and let it --list and --help its way to what it needs. Anthropic's Tool Search showed that even first-party providers see the value in lazy loading. mcp2cli builds on both ideas with a few key differences:。关于这个话题，新收录的资料提供了深入分析
，详情可参考新收录的资料
本文以人工形式完成了事实搜集、资料核查以及内容撰写，在完稿后使用了 ChatGPT 5.2 模型进行了多个段落的润色。。关于这个话题，新收录的资料提供了深入分析
第九条 境内单位或者个人跨境销售下列服务、无形资产，税率为零：