# LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?

arXiv: https://arxiv.org/abs/2508.01780 · HTML: https://mlsanity.com/paper/2508.01780/

## Key facts

- Cited by 48 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 20 of its 48 references that are in the map.
- First posted on arXiv 3 Aug 2025.

## 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, 20 of 20)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (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)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs](https://mlsanity.com/paper/2304.08244/) (2023)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (2025)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models](https://mlsanity.com/paper/2403.07714/) (2024)
- [A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)](https://mlsanity.com/paper/2505.02279/) (2025)
- [Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark](https://mlsanity.com/paper/2405.08355/) (2024)
- [MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models](https://mlsanity.com/paper/2505.16700/) (2025)
- [ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents](https://mlsanity.com/paper/2407.00132/) (2024)
- [ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents](https://mlsanity.com/paper/2505.06416/) (2025)
- [MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models](https://mlsanity.com/paper/2507.12806/) (2025)
- [MCP-Zero: Active Tool Discovery for Autonomous LLM Agents](https://mlsanity.com/paper/2506.01056/) (2025)
- [StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs](https://mlsanity.com/paper/2503.20527/) (2025)

## Built on by (most cited first, 30 of 48)

- [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)
- [Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation](https://mlsanity.com/paper/2605.18740/) (2026)
- [MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers](https://mlsanity.com/paper/2602.00933/) (2026)
- [MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use](https://mlsanity.com/paper/2509.24002/) (2025)
- [SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?](https://mlsanity.com/paper/2603.00718/) (2026)
- [OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents](https://mlsanity.com/paper/2510.24563/) (2025)
- [MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning](https://mlsanity.com/paper/2511.02805/) (2025)
- [From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents](https://mlsanity.com/paper/2603.22386/) (2026)
- [LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries](https://mlsanity.com/paper/2508.15760/) (2025)
- [Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions](https://mlsanity.com/paper/2602.14878/) (2026)
- [Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems](https://mlsanity.com/paper/2511.01854/) (2025)
- [Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents](https://mlsanity.com/paper/2601.20144/) (2026)
- [MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools](https://mlsanity.com/paper/2510.24284/) (2025)
- [M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark](https://mlsanity.com/paper/2511.17729/) (2025)
- [PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems](https://mlsanity.com/paper/2606.22388/) (2026)
- [MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use](https://mlsanity.com/paper/2512.24565/) (2025)
- [ACE-Router: Generalizing History-Aware Routing from MCP Tools to the Agent Web](https://mlsanity.com/paper/2601.08276/) (2026)
- [Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy](https://mlsanity.com/paper/2603.05637/) (2026)
- [SynthTools: A Framework for Scaling Synthetic Tools for Agent Development](https://mlsanity.com/paper/2511.09572/) (2025)
- [TheMCPCompany: Creating General-purpose Agents with Task-specific Tools](https://mlsanity.com/paper/2510.19286/) (2025)
- [FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Financial Tasks](https://mlsanity.com/paper/2604.10015/) (2026)
- [ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox](https://mlsanity.com/paper/2605.10787/) (2026)
- [C-World: A Computer Use Agent Environment Creator](https://mlsanity.com/paper/2601.06328/) (2026)
- [MedMCP-Calc: Benchmarking LLMs for Realistic Medical Calculator Scenarios via MCP Integration](https://mlsanity.com/paper/2601.23049/) (2026)
- [From Tool Orchestration to Code Execution: A Study of MCP Design Choices](https://mlsanity.com/paper/2602.15945/) (2026)
- [MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation](https://mlsanity.com/paper/2606.02470/) (2026)
- [AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments](https://mlsanity.com/paper/2607.05174/) (2026)
- [ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation](https://mlsanity.com/paper/2602.01709/) (2026)
- [Skill Description Deception Attack against Task Routing in Internet of Agents](https://mlsanity.com/paper/2605.09889/) (2026)

## Abstract (arXiv)

Model Context Protocol (MCP) has become a key infrastructure for connecting LLMs with external tools, scaling to 10,000+ MCP servers with diverse tools. Unfortunately, there is still a large gap between real-world MCP usage and current evaluation: they typically assume single-server settings and directly inject tools into the model's context, bypassing the challenges of large-scale retrieval and multi-tool composition. To bridge this gap, we propose LiveMCPBench, which evaluates 95 real-world daily tasks explicitly constructed to stress diverse tools and scaled multi-server routing. The benchmark includes a ready-to-deploy tool suite of 70 servers with 527 tools, ensuring reproducibility without scattered API configuration. We further introduce an LLM-as-a-Judge evaluation framework that directly verifies task outcomes, handling dynamic data sources and multiple valid solution paths. We benchmark 12 state-of-the-art LLMs and observe a substantial performance gap: while Claude-Sonnet-4 reaches 78.95% task success, most models achieve only 30-50%. Our analysis reveals that the active tool composition strongly correlates with task success, whereas retrieval errors account for nearly half of all failures, highlighting retrieval as the dominant bottleneck. Together, these results provide the first large-scale, reproducible diagnosis of MCP agent capabilities and point towards future research on improving retrieval robustness and encouraging effective tool composition. Our code and data are publicly available at https://icip-cas.github.io/LiveMCPBench.