MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

• URL: http://arxiv.org/abs/2509.24002v1
• Date: Sun, 28 Sep 2025 17:53:27 GMT
• Title: MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
• Authors: Zijian Wu, Xiangyan Liu, Xinyuan Zhang, Lingjun Chen, Fanqing Meng, Lingxiao Du, Yiran Zhao, Fanshi Zhang, Yaoqi Ye, Jiawei Wang, Zirui Wang, Jinjie Ni, Yufan Yang, Arvin Xu, Michael Qizhe Shieh,
• Abstract summary: MCPMark is a benchmark designed to evaluate MCP use in a more realistic and comprehensive manner.<n>It consists of $127$ high-quality tasks collaboratively created by domain experts and AI agents.<n>On average, LLMs require $16.2$ execution turns and $17.4$ tool calls per task, significantly surpassing those in previous MCP benchmarks.
• Score: 27.978435634514128
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: MCP standardizes how LLMs interact with external systems, forming the foundation for general agents. However, existing MCP benchmarks remain narrow in scope: they focus on read-heavy tasks or tasks with limited interaction depth, and fail to capture the complexity and realism of real-world workflows. To address this gap, we propose MCPMark, a benchmark designed to evaluate MCP use in a more realistic and comprehensive manner. It consists of $127$ high-quality tasks collaboratively created by domain experts and AI agents. Each task begins with a curated initial state and includes a programmatic script for automatic verification. These tasks demand richer and more diverse interactions with the environment, involving a broad range of create, read, update, and delete (CRUD) operations. We conduct a comprehensive evaluation of cutting-edge LLMs using a minimal agent framework that operates in a tool-calling loop. Empirical results show that the best-performing model, gpt-5-medium, reaches only $52.56$\% pass@1 and $33.86$\% pass^4, while other widely regarded strong models, including claude-sonnet-4 and o3, fall below $30$\% pass@1 and $15$\% pass^4. On average, LLMs require $16.2$ execution turns and $17.4$ tool calls per task, significantly surpassing those in previous MCP benchmarks and highlighting the stress-testing nature of MCPMark.

Related papers

• MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers [5.463884405989425]
  We introduce MCP-Atlas, a large-scale benchmark for evaluating tool-use competency.<n>It includes 1,000 tasks designed to assess tool-use competency in realistic, multi-step orchestrate.<n>We score tasks using a claims-based rubric that awards partial credit based on the factual claims satisfied in the model's final answer.
  arXiv  Detail & Related papers  (2026-01-31T23:19:39Z)
• LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries [38.56775962026289]
  We present LiveMCP-101, a benchmark of 101 carefully curated real-world queries.<n>Experiments show that even frontier LLMs achieve a success rate below 60%.<n>LiveMCP-101 sets a rigorous standard for evaluating real-world agent capabilities.
  arXiv  Detail & Related papers  (2025-08-21T17:55:54Z)
• MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers [86.00932417210477]
  We introduce MCP-Universe, the first comprehensive benchmark specifically designed to evaluate LLMs in realistic and hard tasks through interaction with real-world MCP servers.<n>Our benchmark encompasses 6 core domains spanning 11 different MCP servers: Location Navigation, Repository Management, Financial Analysis, 3D Design, Browser Automation, and Web Searching.<n>We find that even SOTA models such as GPT-5 (43.72%), Grok-4 (33.33%) and Claude-4.0-Sonnet (29.44%) exhibit significant performance limitations.
  arXiv  Detail & Related papers  (2025-08-20T13:28:58Z)
• Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models [9.49963945880421]
  We introduce MCPGAUGE, the first comprehensive evaluation framework for probing LLM-MCP interactions.<n> MCPGAUGE comprises a 160-prompt suite and 25 datasets spanning knowledge comprehension, general reasoning, and code generation.<n>Our large-scale evaluation, spanning six commercial LLMs, 30 MCP tool suites, and both one- and two-turn interaction settings, comprises around 20,000 API calls and over USD 6,000 in computational cost.
  arXiv  Detail & Related papers  (2025-08-18T02:06:05Z)
• LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools? [50.60770039016318]
  We present LiveMCPBench, the first comprehensive benchmark for benchmarking Model Context Protocol (MCP) agents.<n>LiveMCPBench consists of 95 real-world tasks grounded in the MCP ecosystem.<n>Our evaluation covers 10 leading models, with the best-performing model reaching a 78.95% success rate.
  arXiv  Detail & Related papers  (2025-08-03T14:36:42Z)
• MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models [76.72220653705679]
  We introduce MCPEval, an open-source framework that automates end-to-end task generation and deep evaluation of intelligent agents.<n> MCPEval standardizes metrics, seamlessly integrates with native agent tools, and eliminates manual effort in building evaluation pipelines.<n> Empirical results across five real-world domains show its effectiveness in revealing nuanced, domain-specific performance.
  arXiv  Detail & Related papers  (2025-07-17T05:46:27Z)
• EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models [64.70546873396624]
  We present the Extremely Complex Instruction Following Benchmark (EIFBENCH) for evaluating large language models (LLMs)<n>EIFBENCH includes multi-task scenarios that enable comprehensive assessment across diverse task types concurrently.<n>We also propose the Segment Policy Optimization (SegPO) algorithm to enhance the LLM's ability to accurately fulfill multi-task workflow.
  arXiv  Detail & Related papers  (2025-06-10T02:39:55Z)
• MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models [33.250579401886206]
  This paper introduces MCP-RADAR, the first comprehensive benchmark specifically designed to evaluate Large Language Models (LLMs) performance within the Model Context Protocol (MCP) framework.<n> MCP-RADAR features a challenging dataset of 507 tasks spanning six domains: mathematical reasoning, web search, email, calendar, file management, and terminal operations.<n>Unlike traditional benchmarks that rely on subjective human evaluation or binary success metrics, MCP-RADAR adopts objective, quantifiable measurements across multiple task domains.
  arXiv  Detail & Related papers  (2025-05-22T14:02:37Z)
• CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents [49.68117560675367]
  Crab is the first benchmark framework designed to support cross-environment tasks.<n>Our framework supports multiple devices and can be easily extended to any environment with a Python interface.<n>The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 38.01%.
  arXiv  Detail & Related papers  (2024-07-01T17:55:04Z)
• Planning with Multi-Constraints via Collaborative Language Agents [13.550774629515843]
  This paper introduces Planning with Multi-Constraints (PMC), a zero-shot methodology for collaborative multi-agent systems.<n>PMC simplifies complex task planning with constraints by decomposing it into a hierarchy of subordinate tasks.<n>PMC achieved an average 42.68% success rate on TravelPlanner, significantly higher than GPT-4 (2.92%), and outperforming GPT-4 with ReAct on API-Bank by 13.64%.
  arXiv  Detail & Related papers  (2024-05-26T10:33:17Z)
• TaskBench: Benchmarking Large Language Models for Task Automation [82.2932794189585]
  We introduce TaskBench, a framework to evaluate the capability of large language models (LLMs) in task automation. Specifically, task decomposition, tool selection, and parameter prediction are assessed. Our approach combines automated construction with rigorous human verification, ensuring high consistency with human evaluation.
  arXiv  Detail & Related papers  (2023-11-30T18:02:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.