MCP-Injector 研究 120B 模型处理工具故障的表现与 20B 相当
MCP-Injector 研究显示，120B 模型处理现实 MCP 工具故障的能力并不优于 20B 模型。该代理工具基于 1,774 个开源 MCP 仓库的 57,240 条 issue 和 pull request 线程校准故障类型，在 gpt-oss-20B、120B 及三种智能体框架共 1,350 次运行中，故障使任务完成分数从 8.08 降至 3.23，降幅 60%。
Be careful when integrating MCP tools into production.
This work shows that a 120B model handles realistic MCP tool failures no better than a 20B model.
They built MCP-Injector, a proxy that injects faults into MCP tool calls. The fault mix is calibrated on 57,240 issue and pull-request threads from 1,774 open-source MCP repositories, so it reflects how MCP servers fail in practice.
Across 1,350 runs with gpt-oss-20B and 120B and three agent stacks (a custom plan-and-execute loop, OpenAI Agents SDK, LangChain), task-completion score falls 60%, from 8.08 to 3.23 out of 10.
The larger model retains a smaller share of its fault-free score (p = 0.96), and its completion rate under faults is slightly lower: 91.1% vs. 95.6%. Differences between agent stacks are larger than the difference between model sizes.
The paper is accepted at NeurIPS 2026.
The practical takeaway is that if your MCP agents are only tested against tools that always respond correctly, add fault injection to the eval and put the effort into framework-level error handling.
arxiv.org/abs/2610.32555
Chat with Paper: academy.dair.ai/papers/tool-…
来源：dair_ai · x.com