MCP客户端在失败后能否决定做什么？仅结果可操作审计
Can MCP Clients Decide What to Do After Failure? A Result-Only Actionability Audit
AI总结：
本文研究确定性软件仅从完整MCP失败结果中可获取的信息，通过21次服务器失败研究发现MCP结果难提供具体恢复信息，提出六部分可操作概况及故障关闭原型。
AI中文摘要：
收到isError:true的客户端知道出现了问题，但可能仍无机器可读的依据来决定是修复参数、进行身份验证、等待、选择其他工具还是停止。本文研究确定性软件仅能从完整的MCP失败结果中获取什么信息；请求参数、模式、发现历史、身份验证状态、传输元数据、主机策略和应用状态均不在此范围内。我们引入了由六个部分组成的可操作概况，并结合记录级证据进行应用。在对10台可访问的采样服务器上诱导的21次安全失败进行的小型说明性研究中，类型化字段在18个案例中暴露了失败，在8个案例中暴露了宽泛的策略，但未暴露具体原因、目标、可执行修复或重放约束。 prose通常承载更多原因和目标信息，但代价是将语义解释纳入恢复路径。词汇源审计发现了相同的以文本为中心的模式。最后，一个故障关闭原型展示了独立的实验控制平面如何支持确定性分支。结果比生态系统调查或智能体基准更具针对性：在此样本中，完整的MCP结果通常使失败可观察，有时使宽泛的响应成为可能，但很少使具体恢复或安全重放成为自包含操作。
英文摘要：
A client that receives isError:true knows that something went wrong. It may still have no machine-readable basis for deciding whether to fix an argument, authenticate, wait, choose another tool, or stop. This paper studies what deterministic software can learn from a completed MCP failure result alone; request arguments, schemas, discovery history, authen- tication state, transport metadata, host policy, and ap- plication state are outside that boundary. We introduce a six-part actionability profile and apply it with record- level evidence. In a small illustrative study of 21 safely induced failures from ten reachable sampled servers, typed fields expose failure in 18 cases and a broad policy in 8, yet expose no specific cause, target, executable repair, or replay constraint. Prose often carries more cause and target information, at the price of making semantic interpretation part of the recovery path. A lexical source audit finds the same text-centered pat- tern. Finally, a fail-closed prototype demonstrates how a separate experimental control plane could support deterministic branching. The result is deliberately nar- rower than an ecosystem survey or an agent benchmark: completed MCP results often make failure observable, sometimes make a broad response possible, and rarely make concrete recovery or safe replay self-contained in this sample.
