Model Context Protocol

Also known as MCP

Ask about this topic

Overview

Model Context Protocol research studies how AI agents discover and use tools, data sources, and services through a common client-server interface. Approaches include schema and domain-specific tool design, semantic or hybrid retrieval for large tool catalogs, workflow and graph-based planning, and gateways that handle routing, access control, and errors. Evaluations use benchmarks and live environments to test tool selection, multi-step task completion, efficiency, and recovery, while security work examines server trust and the fidelity of tool descriptions. A central challenge is making MCP systems reliable and safe at scale: agents still struggle with long or changing tool sequences, and outcomes depend on metadata, agent scaffolding, and production infrastructure as well as the protocol itself.

Latest papers

CardsList

32 papers5 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. Tool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault Tolerance

    Oct 23, 2026Antonio Ken Iannillo, Joshua Segun Owotogbe, Roberto Natella +3LLM Agent ReliabilityLLM Agent Evaluation

    SnT, University of Luxembourg · Tilburg University · Gran Sasso Science Institute +1

  2. GatewayBench: Unified Capability and Security Evaluation Platform for MCP Gateways

    Oct 16, 2026Yitian Zheng, Zhaorun Chen, Haoyu Li +1Model Context ProtocolAI Agent Security Benchmarks

    Tsinghua University · University of Chicago · University of Illinois Urbana-Champaign

  3. MCPDisCo: Seesaw-Mitigated Tuning for MCP-Native Agents

    Oct 10, 2026Kounianhua Du, Jianxing Liu, Shuai Shao +3RL for LLM AgentsAgentic RL

    Shanghai Jiao Tong University, Shanghai, China · Tencent. Shanghai, China

  4. Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions

    Oct 9, 2026Xiaofan Li, Fengchun Qiao, Xing GaoLLM Tool UseModel Context Protocol

    University of Delaware, Newark, DE, USA · University of South Florida, Tampa, FL, USA

  5. MCP Error Messages Written for Developers Hurt the Most Capable Agents Most

    Sep 28, 2026Xiaonan Xu, Wenjing WuLLM Tool UseModel Context Protocol

    College of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USA · Department of Computer Science, University of Colorado Boulder, Boulder, CO 80309, USA

  6. Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents

    Sep 13, 2026Justice Owusu Agyemang, Michael Agyare, Kwame Opuni-Boachie Obour Agyekum +3LLM Tool UseAgentic Retrieval

    VIA Cybersecurity Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana · Quantum and Assistive Technologies Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana · Ghana Communication Technology University, Ghana

  7. What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain Instead

    Sep 10, 2026Haseeb Mohammed AfsarTool-Use EvaluationModel Context Protocol

    Independent researcher

  8. Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation

    Aug 25, 2026Olympia Saha, Amy Wang, Srinivasan ManoharanTool Discovery for LLM AgentsLLM Tool Use

    PayPal, Inc.

  9. From SQL Generation to Tool Selection: A Domain-Oriented Pattern for MCP Servers

    Aug 22, 2026Bartolomeo BoglioloLLM Tool UseText-to-SQL

  10. The Scaffolding Matters More Than the Interface: A Controlled Comparison of MCP and CLI Tool Use Across Seven Agent Scaffoldings, Five Language Models, and One Software Task

    Aug 9, 2026Marc Alier Forment, María José Casañ Guerrero, Francisco José García-Peñalvo +1AI Coding AgentsLLM Agent Evaluation

    Universitat Politècnica de Catalunya (UPC), Barcelona, Spain · Universidad de Salamanca (USAL), Salamanca, Spain · Universidad del País Vasco / Euskal Herriko Unibertsitatea (UPV/EHU), Donostia-San Sebastián, Spain

  11. LLM within MCP Matters: Measuring Inefficient Resource Utilization Driven by LLMs

    Aug 9, 2026Minhan Cho, Soyoung Park, Kihyeon Jeong +3LLM Inference EfficiencyInstruction Following

    Remember & Company AI Lab · Sungkyunkwan University · National Assembly Research Service +2

  12. Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog

    Jul 23, 2026Bartolomeo BoglioloLogic ProgrammingLLM Reliability

  13. Scalable LLM Agent Tool Access in the Cloud

    Jul 17, 2026Mingxin Li, Enge Song, Yueshang Zuo +27LLM Tool UseModel Context Protocol

    Nanjing University · Alibaba Cloud · Fudan University +3

  14. MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers

    Jul 16, 2026Huanxi Liu, Kun Hu, Jiaqi Liao +6Tool-Use EvaluationAI Agent Benchmarks

    College of Computer Science and Technology, National University of Defense Technology · State Key Laboratory of Complex & Critical Software Environment · National Key Laboratory of Parallel and Distributed Computing

  15. A Large-Scale Dataset of MCP Implementations on GitHub

    Jul 11, 2026Benny Toeppe, Amine Barrak, Emna KsontiniSoftware EngineeringModel Context Protocol

    Oakland University Michigan, USA · University of North Carolina Wilmington North Carolina, USA

  16. DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP Servers

    Jul 10, 2026Jerzy Kamiński, Ilya Galyukshev, Artem Kuznetsov +4Computer-Use Agent BenchmarksLLM Agent Evaluation

    ITMO University · Central University

  17. Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations

    Jul 7, 2026Mohammadreza RashidiAdversarial AttacksMCP Security

    Department of Computer Science AI and Media Analysis Lab Berlin, Germany

  18. MCP Server Architecture Patterns for LLM-Integrated Applications

    Jun 29, 2026Carson Rodrigues, Oysturn VasLLM Tool UseModel Context Protocol

    Celabe · University of Waterloo

  19. A Taxonomy of Runtime Faults in Model Context Protocol Servers

    Jun 3, 2026Joshua Owotogbe, Indika Kumara, Willem-Jan van den Heuvel +3Agent Failure AnalysisModel Context Protocol

    Jheronimus Academy of Data Science and Tilburg University, The Netherlands · University of Sannio, Benevento, Italy · University of Luxembourg, Luxembourg +1

  20. Beyond Prompt-Based Planning: MCP-Native Graph Planning-based Biomedical Agent System

    Jun 3, 2026Zhangtianyi Chen, Florensia Widjaja, Wufei Dai +3Model Context ProtocolGraph-Based Planning

    1The Chinese University of Hong Kong, Shenzhen

  21. MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation

    Jun 1, 2026Wenhao Wang, Peizhi Niu, Gongyi Zou +9LLM Agent EvaluationAI Agent Benchmarks

    Multi-Agent Governance & Intelligence Crew (MAGIC), Shanghai Jiao Tong University, Shanghai, China · Department of Computer Science and Technology, Zhejiang University, Hangzhou, China · University of Illinois at Urbana-Champaign, Illinois, USA +2

  22. Attested Tool-Server Admission: A Security Extension to the Model Context Protocol

    May 22, 2026Alfredo MetereMCP SecurityAI Agent Security

    Enclawed LLC

  23. Resilient Write: A Six-Layer Durable Write Surface for LLM Coding Agents

    Apr 12, 2026Justice Owusu Agyemang, Jerry John Kponyo, Elliot Amponsah +2LLM Agent ReliabilityAI Coding Agents

    Sperixlabs, Ghana · Kwame Nkrumah University of Science and Technology, Kumasi, Ghana · VIA Cybersecurity Lab, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana

  24. PHMForge: Evaluating LLM Agents on Industrial Prognostics through MCP-Native, Algorithm-Grounded Tools

    Apr 2, 2026Yusheng Li, Tianjun Feng, Yunfeng Chen +6LLM Agent EvaluationAI Agent Benchmarks

    Columbia University · Georgia Institute of Technology · IBM, New York

  25. IndustriConnect: MCP Adapters and Mock-First Evaluation for AI-Assisted Industrial Operations

    Mar 25, 2026Melwin Xavier, Melveena Jolly, Vaisakh M A +1Industrial AutomationAI Agent Benchmarks

    Lule˚a tekniska universitet, Sweden · Independent Researcher

  26. Bypassing Document Ingestion: An MCP Approach to Financial Q&A

    Mar 19, 2026Sasan Mansouri, Edoardo Pilla, Mark Wahrenburg +1Financial QAModel Context Protocol

    University of Groningen · Goethe University Frankfurt · Halle Institute for Economic Research (IWH) and Martin Luther University Halle-Wittenberg

  27. Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection

    Mar 19, 2026Sarat Mudunuri, Jian Wan, Ally Qin +1LLM Tool UseModel Context Protocol

    Primary contributor

  28. Open Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database

    Mar 16, 2026Madhulatha Mandarapu, Sandeep KunkunuruBiomedical KGsKG Construction

    VaidhyaMegha Private Limited, India

  29. Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol

    Mar 13, 2026Abhinav Singh ParmarLLM Agent Tool GenerationLLM Agent Orchestration

    A Preprint

  30. Bridging Protocol and Production: Design Patterns for Deploying AI Agents with Model Context Protocol

    Mar 12, 2026Vasundra SrinivasanTool-Using AgentsAI Agent Reliability