{"slug": "mcp-bench-benchmarking-tool-using-llm-agents-with-complex-real-world-tasks-2025", "title": "MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks 2025", "summary": "Researchers introduced MCP-Bench, a benchmark for evaluating large language models (LLMs) on realistic multi-step tasks requiring tool use, built on the Model Context Protocol (MCP) and connecting to 28 live MCP servers spanning 250 tools across finance, traveling, scientific computing, and academic search. Experiments on 20 advanced LLMs revealed persistent challenges in tool-level schema understanding, trajectory-level planning, and task completion, highlighting gaps in current AI agent capabilities.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 28 Aug 2025]\n\n# Title:MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers\n\n[View PDF](/pdf/2508.20453)\n\nAbstract:We introduce MCP-Bench, a benchmark for evaluating large language models (LLMs) on realistic, multi-step tasks that demand tool use, cross-tool coordination, precise parameter control, and planning/reasoning for solving tasks. Built on the Model Context Protocol (MCP), MCP-Bench connects LLMs to 28 representative live MCP servers spanning 250 tools across domains such as finance, traveling, scientific computing, and academic search. Unlike prior API-based benchmarks, each MCP server provides a set of complementary tools designed to work together, enabling the construction of authentic, multi-step tasks with rich input-output coupling. Tasks in MCP-Bench test agents' ability to retrieve relevant tools from fuzzy instructions without explicit tool names, plan multi-hop execution trajectories for complex objectives, ground responses in intermediate tool outputs, and orchestrate cross-domain workflows - capabilities not adequately evaluated by existing benchmarks that rely on explicit tool specifications, shallow few-step workflows, and isolated domain operations. We propose a multi-faceted evaluation framework covering tool-level schema understanding and usage, trajectory-level planning, and task completion. Experiments on 20 advanced LLMs reveal persistent challenges in MCP-Bench. Code and data:[this https URL].\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/mcp-bench-benchmarking-tool-using-llm-agents-with-complex-real-world-tasks-2025", "canonical_source": "https://arxiv.org/abs/2508.20453", "published_at": "2026-08-05 14:21:44+00:00", "updated_at": "2026-08-05 14:37:26.023053+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-research", "ai-tools"], "entities": ["MCP-Bench", "Model Context Protocol", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/mcp-bench-benchmarking-tool-using-llm-agents-with-complex-real-world-tasks-2025", "markdown": "https://wpnews.pro/news/mcp-bench-benchmarking-tool-using-llm-agents-with-complex-real-world-tasks-2025.md", "text": "https://wpnews.pro/news/mcp-bench-benchmarking-tool-using-llm-agents-with-complex-real-world-tasks-2025.txt", "jsonld": "https://wpnews.pro/news/mcp-bench-benchmarking-tool-using-llm-agents-with-complex-real-world-tasks-2025.jsonld"}}