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

arXiv: https://arxiv.org/abs/2509.24002 · HTML: https://mlsanity.com/paper/2509.24002/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 40 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 29 of 29)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers](https://mlsanity.com/paper/2508.14704/) (2025)
- [MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models](https://mlsanity.com/paper/2505.16700/) (2025)
- [LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?](https://mlsanity.com/paper/2508.01780/) (2025)
- [MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents](https://mlsanity.com/paper/2506.07672/) (2025)
- [MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models](https://mlsanity.com/paper/2507.12806/) (2025)
- [MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools](https://mlsanity.com/paper/2509.09734/) (2025)
- [LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries](https://mlsanity.com/paper/2508.15760/) (2025)

## Built on by (most cited first, 30 of 39)

- [Kimi K3: Open Frontier Intelligence](https://mlsanity.com/paper/2607.24653/) (2026)
- [MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers](https://mlsanity.com/paper/2602.00933/) (2026)
- [Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents](https://mlsanity.com/paper/2602.13379/) (2026)
- [AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts](https://mlsanity.com/paper/2601.11044/) (2026)
- [Qwen-AgentWorld: Language World Models for General Agents](https://mlsanity.com/paper/2606.24597/) (2026)
- [OmniGAIA: Towards Native Omni-Modal AI Agents](https://mlsanity.com/paper/2602.22897/) (2026)
- [ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents](https://mlsanity.com/paper/2604.23781/) (2026)
- [TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications](https://mlsanity.com/paper/2510.18586/) (2025)
- [LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth](https://mlsanity.com/paper/2602.07962/) (2026)
- [World of Workflows: A Benchmark for Bringing World Models to Enterprise Systems](https://mlsanity.com/paper/2601.22130/) (2026)
- [Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application](https://mlsanity.com/paper/2606.12191/) (2026)
- [OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation](https://mlsanity.com/paper/2604.10866/) (2026)
- [CodeDelegator: Mitigating Context Pollution via Role Separation in Code-as-Action Agents](https://mlsanity.com/paper/2601.14914/) (2026)
- [PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools](https://mlsanity.com/paper/2604.01532/) (2026)
- [From Tool Orchestration to Code Execution: A Study of MCP Design Choices](https://mlsanity.com/paper/2602.15945/) (2026)
- [One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows](https://mlsanity.com/paper/2608.19741/) (2026)
- [What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents](https://mlsanity.com/paper/2608.27260/) (2026)
- [Where Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents](https://mlsanity.com/paper/2609.29095/) (2026)
- [ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation](https://mlsanity.com/paper/2602.01709/) (2026)
- [MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security](https://mlsanity.com/paper/2604.07551/) (2026)
- [Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback](https://mlsanity.com/paper/2605.17453/) (2026)
- [E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios](https://mlsanity.com/paper/2607.23722/) (2026)
- [PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents](https://mlsanity.com/paper/2608.24509/) (2026)
- [AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories](https://mlsanity.com/paper/2609.05837/) (2026)
- [EdgeRunner 20B: Military Task Parity with GPT-5 while Running on the Edge](https://mlsanity.com/paper/2510.26550/) (2025)
- [Can LLM Infer Risk Information From MCP Server System Logs?](https://mlsanity.com/paper/2511.05867/) (2025)
- [AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale](https://mlsanity.com/paper/2608.20634/) (2026)
- [Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH](https://mlsanity.com/paper/2606.13994/) (2026)
- [Autonomous Event-Driven Multi-Agent Orchestration for Enterprise AI at Scale](https://mlsanity.com/paper/2606.20058/) (2026)
- [Learning with a Single Rollout via Pass@k Policy Optimization](https://mlsanity.com/paper/2606.25451/) (2026)

## Abstract (arXiv)

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% pass4, while other widely regarded strong models, including claude-sonnet-4 and o3, fall below 30% pass@1 and 15% pass4. 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.