# MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers

arXiv: https://arxiv.org/abs/2602.00933 · HTML: https://mlsanity.com/paper/2602.00933/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration](https://mlsanity.com/paper/1802.08802/) (2018)
- [MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use](https://mlsanity.com/paper/2310.03128/) (2023)
- [MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers](https://mlsanity.com/paper/2508.14704/) (2025)
- [The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution](https://mlsanity.com/paper/2510.25726/) (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)
- [MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use](https://mlsanity.com/paper/2509.24002/) (2025)
- [MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models](https://mlsanity.com/paper/2507.12806/) (2025)
- [ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios](https://mlsanity.com/paper/2401.00741/) (2024)
- [MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use](https://mlsanity.com/paper/2508.16260/) (2025)
- [Why am I Still Seeing This: Measuring the Effectiveness Of Ad Controls and Explanations in AI-Mediated Ad Targeting Systems](https://mlsanity.com/paper/2408.11910/) (2024)

## Built on by (most cited first, 30 of 53)

- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Kimi K3: Open Frontier Intelligence](https://mlsanity.com/paper/2607.24653/) (2026)
- [Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence](https://mlsanity.com/paper/2604.18292/) (2026)
- [Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents](https://mlsanity.com/paper/2605.30621/) (2026)
- [ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces](https://mlsanity.com/paper/2604.05172/) (2026)
- [SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?](https://mlsanity.com/paper/2603.00718/) (2026)
- [HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?](https://mlsanity.com/paper/2604.09408/) (2026)
- [Reward Hacking in Rubric-Based Reinforcement Learning](https://mlsanity.com/paper/2605.12474/) (2026)
- [Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities](https://mlsanity.com/paper/2602.05073/) (2026)
- [EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL](https://mlsanity.com/paper/2605.18703/) (2026)
- [From Question Answering to Task Completion: A Survey on Agent System and Harness Design](https://mlsanity.com/paper/2606.20683/) (2026)
- [Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model](https://mlsanity.com/paper/2607.22083/) (2026)
- [Tracing Agentic Failure from the Flow of Success](https://mlsanity.com/paper/2607.12747/) (2026)
- [OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation](https://mlsanity.com/paper/2604.10866/) (2026)
- [Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation](https://mlsanity.com/paper/2607.08938/) (2026)
- [LHAW: Controllable Underspecification for Long-Horizon Tasks](https://mlsanity.com/paper/2602.10525/) (2026)
- [CocoaBench: Evaluating Unified Digital Agents in the Wild](https://mlsanity.com/paper/2604.11201/) (2026)
- [From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems](https://mlsanity.com/paper/2608.15127/) (2026)
- [Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design](https://mlsanity.com/paper/2604.16279/) (2026)
- [Ask Early, Ask Late, Ask Right: When Does Clarification Timing Matter for Long-Horizon Agents?](https://mlsanity.com/paper/2605.07937/) (2026)
- [AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?](https://mlsanity.com/paper/2608.00155/) (2026)
- [From Tool Orchestration to Code Execution: A Study of MCP Design Choices](https://mlsanity.com/paper/2602.15945/) (2026)
- [MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents](https://mlsanity.com/paper/2607.11818/) (2026)
- [Solar Open 2 Technical Report](https://mlsanity.com/paper/2607.20062/) (2026)
- [One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows](https://mlsanity.com/paper/2608.19741/) (2026)
- [ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer](https://mlsanity.com/paper/2606.05548/) (2026)
- [E-Bench: Benchmarking Multi-Step Tool-Use Agents in Real-World Product Scenarios](https://mlsanity.com/paper/2607.23722/) (2026)
- [LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing](https://mlsanity.com/paper/2608.01662/) (2026)
- [Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools](https://mlsanity.com/paper/2608.04719/) (2026)

## Abstract (arXiv)

The Model Context Protocol (MCP) is emerging as a standard interface through which large language model (LLM) agents discover and invoke external tools. However, existing MCP evaluations fall short along three key axes: realistic multi-step workflows with cross-server orchestration, breadth across authentic MCP servers rather than mocks, and structured, reproducible claim-level scoring disentangled from agent verbosity or style. We introduce MCP-Atlas, a benchmark for measuring tool-use competency against production MCP servers. MCP-Atlas contains 1,000 natural-language tasks written and verified by human experts spanning 36 real MCP servers and 220 tools. Prompts do not specify servers, tools, or parameters, requiring agents to identify relevant tools among semantically plausible distractors and to compose multi-step, cross-server workflows. Each task is scored with a claim-level rubric, where final answers are scored against atomic factual claims grounded in tool outputs. This answer-centric scoring permits valid alternative tool-call trajectories to receive credit. We pair this with an 11-category diagnostic taxonomy that disentangles tool-call failures from cognitive failures in task understanding, synthesis, parsing, and stopping. Evaluating 20 frontier models from six providers under matched task-level conditions, we find pass rates up to 82.2% at a 0.75 claim coverage threshold and a clear three-tier performance structure. Automated diagnostics show that 63.3% of diagnosed failures are cognitive rather than tool-call related. Notably, several high-performing models fail after successful tool execution due to premature stopping or incorrect synthesis. We release the task schema, containerized harness, claim evaluator, and a 500-task public split, while reserving a 500-task private split to preserve leaderboard integrity. The code is at https://github.com/scaleapi/mcp-atlas.