面试题库

7 天 MCP：把工具接进任何 Agent

D3 resources 与 prompts：URI 模板、变更通知、进度与日志、分页，以及客户端能力

• 同一份数据，做成 MCP 资源和做成工具有什么区别？你按什么标准选？For the same data, what is the difference between exposing it as an MCP resource versus a tool, and how do you choose?

  国内高频海外高频基础#primitives#server-design

  分析过程 · 先想清楚再作答

  1. 这题在筛「有没有真的设计过服务端」。答成「资源是只读的、工具会改数据」只能算及格，因为只读的检索照样该做成工具，区分度全在这一步。
  2. 拆法：不要问「它是什么」，问「这一次由谁决定用不用它」。规范把资源定成应用驱动——由宿主应用或用户挑；工具是模型控制——模型看着描述自己调。控制方定了，出错时该找谁负责也就定了。
  3. 再补一条更实用的判据：能不能被枚举。资源要出现在一张可翻页的清单里让人挑，所以「搜索代码」这种输入空间无限的能力，哪怕完全只读也必须做成工具。
  4. 结论：只读、可枚举、希望用户在界面上挑的做成资源；有副作用、或需要模型自己判断时机、或无法枚举的做成工具。
  5. 生产视角要主动加一句成本：工具定义不管用不用，每轮都要塞进请求；资源不被选中就一个 token 都不占。三千篇文档做成三千个工具会直接撑爆上下文，做成资源则按需付费。
  6. 可预期的追问：那提示模板算第几种？答案是第三种，由用户显式选中，典型形态是斜杠命令——三种原语的差别只在控制方，不在能力。

  How to reason about it · think before answering

  1. This screens for real server design experience. Saying resources are read-only and tools mutate scores a pass at best, because read-only search still belongs in a tool.
  2. Reframe it: do not ask what the data is, ask who decides to use it this time. The spec makes resources application-driven, picked by the host or the user, while tools are model-controlled. Fixing the controller also fixes who is accountable when it goes wrong.
  3. Add the practical test: enumerability. A resource has to appear in a paginated list a human can pick from, so a code search with an unbounded input space must be a tool even though it never writes anything.
  4. Conclusion: read-only, enumerable, user-selectable becomes a resource; side-effecting, model-timed, or non-enumerable becomes a tool.
  5. Bring up cost unprompted: tool definitions ship on every turn whether used or not, while an unselected resource costs zero tokens. Three thousand documents as three thousand tools blows up the context window; as resources they are pay-per-use.
  6. Likely follow-up: where do prompts fit? They are the third primitive, user-selected and usually surfaced as slash commands — the three differ only by who controls them.

  答题要点

  • 资源是应用驱动的，由宿主或用户挑；工具是模型控制的，由模型看描述自己调
  • 能不能枚举是最实用的分界线：搜索这类输入空间无限的能力即使只读也做成工具
  • 成本上工具定义每轮都占上下文，资源不被选中就不花钱，大规模知识库必须走资源
  • 控制方决定了出错时找谁负责：模型选错是描述问题，用户选错是命名问题，应用塞错是产品问题

  Key points

  • Resources are application-driven and picked by host or user; tools are model-controlled and chosen from their descriptions
  • Enumerability is the practical dividing line: unbounded-input capabilities like search stay tools even when read-only
  • Cost-wise tool definitions occupy context every turn while unselected resources cost nothing, so large corpora must be resources
  • The controller determines accountability: bad tool choice means bad descriptions, bad prompt choice means bad naming, bad resource injection is a product problem