📰 2026-03-17 03:00 更新
🔸 Apideck CLI – An AI-agent interface with much lower context consumption than MCP / Apideck CLI –与MCP相比，具有低得多的上下文消耗的人工智能代理界面
🔗 Apideck CLI – An AI-agent interface with much lower context consumption than MCP
🔥 77 points
原文:
The problem nobody talks about at demo scale Here’s a scenario that’ll feel familiar if you’ve wired up MCP servers for anything beyond a demo. You connect GitHub, Slack, and Sentry. Three services, maybe 40 tools total. Before your agent has read a single user message, 55,000 tokens of tool definitions are sitting in the context window. That’s over a quarter of Claude’s 200k limit. Gone. It gets worse. Each MCP tool costs 550–1,400 tokens for its name, description, JSON schema, field descrip…
译文:
没有人在演示规模上谈论的问题如果您为演示以外的任何东西连接了MCP服务器，这里有一个场景会让您感到熟悉。您可以连接GitHub、Slack和Sentry。三项服务，总共可能有40个工具。在代理读取单个用户消息之前， 55,000个工具定义令牌位于上下文窗口中。这超过了克劳德20万上限的四分之一。不见了。情况变得更糟了。每个MCP工具的成本为550-1,400令牌 名称、描述、JSON架构、字段描述…
自动更新 · 正文抓取 · 双语翻译