MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use
This work addresses the need for better evaluation of LLM agents using MCP tools, though it is incremental as it builds on existing MCP frameworks.
The authors tackled the problem of evaluating LLM agents' tool-use capabilities by proposing MCPAgentBench, a benchmark with real-world tasks and simulated tools, which revealed significant performance differences among models in handling complex tool invocations.
Large Language Models (LLMs) are increasingly serving as autonomous agents, and their utilization of external tools via the Model Context Protocol (MCP) is considered a future trend. Current MCP evaluation sets suffer from issues such as reliance on external MCP services and a lack of difficulty awareness. To address these limitations, we propose MCPAgentBench, a benchmark based on real-world MCP definitions designed to evaluate the tool-use capabilities of agents. We construct a dataset containing authentic tasks and simulated MCP tools. The evaluation employs a dynamic sandbox environment that presents agents with candidate tool lists containing distractors, thereby testing their tool selection and discrimination abilities. Furthermore, we introduce comprehensive metrics to measure both task completion rates and execution efficiency. Experiments conducted on various latest mainstream Large Language Models reveal significant performance differences in handling complex, multi-step tool invocations. All code is open-source at Github.