Preprint
Jul 2026
DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers
DynamicMCPBench is presented, a reusable framework rather than a fixed dataset that turns benchmark construction into something practitioners can rerun on their own servers and models, while exposing a consistent inability of current agents to handle long, multi-step agentic tasks.
Jerzy Kamiński, Ilya Galyukshev, Artem Kuznetsov et al.
· 0 citations