MCP-Universe
agents
MCP-Universe evaluates LLMs on complex multi-step agentic tasks using Model Context Protocol (MCP) tools across diverse interactive environments, testing planning, tool orchestration, and task completion.
Methodology
Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: agents, tool_calling. Language: en. Verified by llm-stats: no.