MCP-Bench

Emerging

4papers using it

2025first seen

MCP-Bench is a benchmark dataset that contains tasks designed to evaluate the execution feasibility of tool workflows across live MCP servers and a variety of tools.

🔎 Find this dataset

Papers using MCP-Bench (4)

Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents2026

MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments2026

From Tool Orchestration To Code Execution: A Study Of MCP Design Choices2026

Cp-agent: Agentic Constraint Programming2025