mlsanityData to 14 Oct 2026

MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools

arXiv 2510.24284 ↗First posted 28 Oct 2025cs.AIcited by 11

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Large Language Models (LLMs) increasingly rely on external tools to perform complex, realistic tasks, yet their ability to utilize the rapidly expanding Model Contextual Protocol (MCP) ecosystem remains limited. Existing MCP research covers few servers, depends on costly manual curation, and lacks training support, hindering progress toward real-world deployment. To overcome these limitations, we introduce MCP-Flow, an automated web-agent-driven pipeline for large-scale server discovery, data synthesis, and model training. MCP-Flow collects and filters data from 1166 servers and 11536 tools, producing 68733 high-quality instruction-function call pairs and 6439 trajectories, far exceeding prior work in scale and diversity. Extensive experiments demonstrate MCP-Flow's effectiveness in driving superior MCP tool selection, function-call generation, and enhanced agentic task performance. MCP-Flow thus provides a scalable foundation for advancing LLM agents' proficiency in real-world MCP environments. MCP-Flow is publicly available at https://github.com/wwh0411/MCP-Flow.

Key facts. Cited by 11 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 30 of its 53 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

30 of 53 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries21 Aug
  2. 2025MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers20 Aug
  3. 2025LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?3 Aug
  4. 2025MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models17 Jul
  5. 2025MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models22 May
  6. 2024NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models15 Oct
  7. 2024ToolACE: Winning the Points of LLM Function Calling2 Sep
  8. 2024APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets26 Jun
  9. 2024Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark14 May
  10. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction11 Jan
  11. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul

Other references · 19

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  4. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  5. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  6. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  7. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  8. 2021ZeRO-Offload: Democratizing Billion-Scale Model Trainingcited by 341
  9. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 335
  10. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  11. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 144
  12. 2025Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Serverscited by 65
7 more
  1. 2025MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agentscited by 38
  2. 2025MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmarkcited by 32
  3. 2024KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Servercited by 11
  4. 2025MobileA3gent: Training Mobile GUI Agents Using Decentralized Self-Sourced Data from Diverse Userscited by 10
  5. 2025Evaluation Report on MCP Serverscited by 9
  6. 2025A Large-Scale Evolvable Dataset for Model Context Protocol Ecosystem and Security Analysiscited by 7
  7. 2025InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agentscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 11.

11 papers.

  1. 2026Silo-Bench: A Scalable Environment for Evaluating Distributed Coordination in Multi-Agent LLM Systemscited by 20
  2. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  3. 2026SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Contextcited by 6
  4. 2026SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agentscited by 4
  5. 2026MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulationcited by 3
  6. 2026Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operationscited by 2
  7. 2026Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIscited by 2
  8. 2026MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement Learningcited by 1
  9. 2026FedGUI: Benchmarking Federated GUI Agents across Heterogeneous Platforms, Devices, and Operating Systemscited by 0
  10. 2026MCPDisCo: Seesaw-Mitigated Tuning for MCP-Native Agentscited by 0
  11. 2026Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environmentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
  2. 2026DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers
  3. 2025ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents
  4. 2025Help or Hurdle? Rethinking Model Context Protocol-Augmented Large Language Models
  5. 2025MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
  6. 2025MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Use
  7. 2025Network and Systems Performance Characterization of MCP-Enabled LLM Agents
  8. 2025MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use