Model Context Protocol

Ask about this topic

Momentum

11 papers in the last four weeks, up 267% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 90

All topics
CardsList

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

    Sep 28, 2026Xiaonan Xu, Wenjing WuModel Context ProtocolFundamental Limits

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

  2. HTN Planning as a Coordination Layer for Multi-Server MCP Tool Orchestration

    Sep 27, 2026Eliott Jacopin, Éric Jacopin, Koichi TakahashiModel Context ProtocolCoordination

    RIKEN, Kobe, Japan · Cosmic AI, France

  3. Realize What Matters: Principled Context Representation for Large-Scale Reasoning

    Sep 23, 2026Michael Theologitis, Dean Light, Shuyue Stella Li +3Contextual ReasoningRelevance

    University of Washington

  4. A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem

    Sep 22, 2026Laizhen Li, Xuan Wang, Peicheng Zhao +4Model Context ProtocolHijacking

    Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Nanyang Technological University +3

  5. TuiML: Machine Learning for AI Agents

    Sep 16, 2026Nilesh Verma, Nick Lim, Albert Bifet +1Artificial Intelligence AgentsModel Context Protocol

    AI Institute, University of Waikato Hamilton 3216, New Zealand · LTCI, T´el´ecom Paris, Institut Polytechnique de Paris 19 place Marguerite Perey, 91120 Palaiseau, France

  6. When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary

    Sep 14, 2026Artem Trofimov, Boris NovikovTool InvocationAgentic Workflow Design

    AVIV Group · Independent Researcher

  7. The Stochastic Deputy: Structural Tenant Isolation for Tool-Using LLM Agents

    Sep 13, 2026Mirza Samad Ahmed Baig, Syeda Anshrah Gillani, Asher Ali +1Language-Model AgentsLarge Language Model Agents

    1*Fandaqah, Al Khobar, Saudi Arabia. · 2Heidelberg University, Heidelberg, Germany.

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

    Sep 12, 2026Haseeb Mohammed AfsarModel Context ProtocolControlling Tool Use

    Independent researcher

  9. No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

    Sep 9, 2026Zehua Zhang, Jie Hu, Pratham Hegde +13Common Vulnerabilities And ExposureModel Vulnerabilities

    School of Computing and Augmented Intelligence, Arizona State University

  10. Beyond Fluent Generation: A CPU Reliability Benchmark for MCP-Style Tool Calling in Sub-2B Small Language Models for Edge Deployment

    Sep 7, 2026Abrar Shahriar Qurat-Ul-Ain MastoiSmall Large Language ModelsModel Context Protocol

    University of the West of England, Bristol,BS16 1QY United Kingdom

  11. How Long Until Your Robot Ignores You? A Safety Benchmark for LLM Orchestrators in Human-Humanoid Collaboration

    Sep 7, 2026Aulon Bajrami, Mohamed Elshamouty, Werner KrausSafety BenchmarksLarge Language Model Workflows

    Fraunhofer IPA Stuttgart, Germany

  12. Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study

    Sep 1, 2026Arpan Kumar MahapatraModel Context ProtocolAgentic Deployments

  13. Orchestra: Corroboration-Based Regulatory Candidate Discovery via Composed Bioinformatics MCP Agents

    Aug 27, 2026Jose A. BirdRegulatory NetworksRegulation

    Independent Researcher, Bird AI Solutions

  14. A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem

    Aug 11, 2026Suraj Kumar, Amy Wang, Srinivasan ManoharanModel Context ProtocolAuthentication

    Enterprise AI Platform Engineering

  15. 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 +1Coding AgentsModel Context Protocol

    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

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

    Aug 9, 2026Minhan Cho, Soyoung Park, Kihyeon Jeong +3Model Context ProtocolExacerbate Systemic Inefficiencies

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

  17. ZhuLong: Execution-Grounded LLM Agent for EDA Scripting with Offline API Self-Exploration

    Aug 8, 2026Yang Liu, Shiwei Hou, Xiyuan Chen +13Large Language Model AgentsEvaluation Agent

    Changxin Memory Technologies, Inc. China

  18. Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools

    Aug 5, 2026Atul Anand, Sourav ChattarajControlling Tool UseLarge Language Model Agents

  19. Exposed by Design: A Dynamic Security Assessment of Internet-Facing MCP Servers at Scale

    Jul 31, 2026Nicolás PadillaSecurity EvaluationModel Context Protocol

    CobaltoSec

  20. HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following

    Jul 28, 2026Liudas Panavas, Sebastian Minus, Bradley Monton +4Model Context Protocol

    Surge AI*

  21. Hybrid Analysis for Secure MCP Tool Use in LLM Agents

    Jul 28, 2026Ping He, Yuexiang Xie, Yaliang Li +1Large Language Model SafetyLarge Language Model Agents

    Zhejiang University · Alibaba Group

  22. A Comparative Study of MCP and A2A for Inter-Agent Coordination in LLM-Based Systems

    Jul 26, 2026Ionut Predoaia, Tuong Manh Vu, Konstantinos Barmpis +2Model Context ProtocolAgent2Agent

    University of York, York, United Kingdom

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

    Jul 23, 2026Bartolomeo BoglioloLLM Reasoning StrategiesDeduction

  24. ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems

    Jul 20, 2026Om Narayan, Rashmi Jyoti, Ramkinker SinghThreat DetectionModel Context Protocol

    Computer Science New York University New York, USA · Cybersecurity University of Maryland, College Park MD, USA · Carnegie Mellon University Pittsburgh, USA

  25. DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

    Jul 18, 2026Runming He, Zhen Hao Wong, Hao Liang +4Large Language Model WorkflowsTaxonomy-Driven Dataflow Model

    Peking University · Institute for Advanced Algorithms Research, Shanghai · Zhongguancun Academy

  26. Scalable LLM Agent Tool Access in the Cloud

    Jul 17, 2026Mingxin Li, Enge Song, Yueshang Zuo +27Model Context ProtocolLarge Language Model Agents

    Nanjing University · Alibaba Cloud · Fudan University +3

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

    Jul 16, 2026Huanxi Liu, Kun Hu, Jiaqi Liao +6Model Context ProtocolAgentic Workflows

    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

  28. AgentCheck: A Reproduce-Intervene-Mitigate Workbench for LLM Agents over MCP

    Jul 13, 2026Aritra Mazumder, Nusrat jahan LiaLarge Language Model AgentsRetrying

    University of Utah · University of Dhaka

  29. When Does Restricting a Coding Agent to execute_code Help? A Regime ×\times Agent-Design Ablation

    Jul 12, 2026Hong Yang, Qi Yu, Travis DesellCoding AgentsSmooth Execution

    Rochester Institute of Technology Rochester, New York, USA

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

    Jul 11, 2026Benny Toeppe, Amine Barrak, Emna KsontiniModel Context ProtocolSchema

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

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

    Jul 10, 2026Jerzy Kamiński, Ilya Galyukshev, Artem Kuznetsov +4Agentic BenchmarksLarge Language Model Agents

    ITMO University · Central University

  32. 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 RashidiModel Context ProtocolMetadata

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

  33. Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI

    Jul 3, 2026Romain Gerard, Assmaa Zeghaider, Yan GuoLarge Language Model SafetyLarge Language Model Agents

    University of Science and Technology of China, Hefei, China · Suzhou Institute for Advanced Research, University of Science and Technology of China

  34. ContextNest: Verifiable Context Governance for Autonomous AI Agent

    Jul 2, 2026Misha Sulpovar, Benn R. Konsynski, Qaish Kanchwala +1GovernanceContext-Awareness

    PromptOwl, LLC · Goizueta Business School, Emory University · IBM Research +1

  35. Governance Gaps in Agent Interoperability Protocols: What MCP, A2A, and ACP Cannot Express

    Jun 30, 2026Richard Kang, Yudho DiponegoroGovernanceInteroperability

    DoiT International

  36. MCP Server Architecture Patterns for LLM-Integrated Applications

    Jun 29, 2026Carson Rodrigues, Oysturn VasModel Context ProtocolVoice Agents

    Celabe · University of Waterloo

  37. From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes

    Jun 27, 2026Ting LiuModel Context ProtocolRuntime Enforcement

    SymbolicLight Research Foshan, Guangdong, China

  38. LAMP: Lean-based Agentic framework with MCP and Proof Repair

    Jun 27, 2026Santhana Srinivasan R, Maithilee PatawarTheorem ProvingCombinations

    Indian Institute of Information Technology, Design and Manufacturing, Kancheepuram

  39. ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP

    Jun 25, 2026Liwei Liu, Tianzhu Han, Zijian Liu +2PoisoningModel Context Protocol

    Shanghai Jiao Tong University · Shanghai, China

  40. Context-Aware Generative AI for Automated Telecom Test Script Generation

    Jun 19, 2026Gautam Prasad, Chandramohan T. N., Joy BoseTest GenerationMobile Networks

    Ericsson R&D Bangalore

  41. Complexity and Scale in AI-Assisted Workflow Management: A Federated Learning Case Study

    Jun 16, 2026Komal Thareja, Hamza Safri, Rajiv Mayani +2Scientific WorkflowsAgentic Workflow Design

    RENCI, University of North Carolina at Chapel Hill, NC, USA · Information Sciences Institute, University of Southern California, Marina del Rey, CA, USA

  42. ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents

    Jun 16, 2026Ander Alvarez, Santhiya Rajan, Samuel Mugel +1Model Context ProtocolFacts

    1Multiverse Computing, Parque Cientifico y Tecnol´ogico de Gipuzkoa, Paseo de Miram´on, 170, 20014 Donostia / San Sebasti´an, Spain · 2Multiverse Computing, Centre for Social Innovation, 192 Spadina Avenue Suite 509, Toronto, ON M5T 2C2, Canada · 3Donostia International Physics Center, Paseo Manuel de Lardizabal 4, E-20018 San Sebasti´an, Spain +1

  43. PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents

    Jun 10, 2026Ripon Chandra Malo, Tong QiuCoding AgentsModel Context Protocol

    University of Utah

  44. Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs

    Jun 9, 2026Saeid Jamshidi, Amin Nikanjam, Arghavan Moradi Dakhel +2Model Context ProtocolMulti-Turn Interactions

    SWAT Laboratory, Polytechnique Montréal, Montréal, QC, Canada · Huawei Distributed Scheduling and Data Engine Lab, Montr´eal, QC, Canada

  45. Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents

    Jun 8, 2026Abhilasha Lodha, Mahsa Pahlavikhah Varnosfaderani, Abir Chakraborty +1Large Language Model Tool UseModel Context Protocol

    Microsoft

  46. VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation

    Jun 6, 2026Harshil Patel, Kunal PaiModel Context ProtocolExploitation

    Department of Computer Science, University of California, Davis, CA, USA.

  47. TokenMizer: Graph-Structured Session Memory for Long-Horizon LLM Context Management

    Jun 4, 2026Shweta MishraFactual RecallModel Context Protocol

    Independent Researcher, India.

  48. Queen-Bee Agents: A BeeSpec-Centered Architecture for Governed Enterprise MCP Orchestration

    Jun 4, 2026Dutao Zhang, LiaotianEnterprise SystemsOrchestration

    Macao Polytechnic University

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

    Jun 3, 2026Joshua Owotogbe, Indika Kumara, Willem-Jan van den Heuvel +3Model Context ProtocolRuntime

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

  50. Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications

    Jun 3, 2026Yutao Shi, Xiaohan Zhang, Xiangjing Zhang +5Model Context ProtocolProgram Analysis

    Fudan University, China

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

    Jun 3, 2026Zhangtianyi Chen, Florensia Widjaja, Wufei Dai +3Multi-Agent WorkflowsBioinformatics

    1The Chinese University of Hong Kong, Shenzhen

  52. Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments

    Jun 2, 2026Ibrahim Abdelaziz, Asim Munawar, Kinjal Basu +4Large Language Model WorkflowsModel Context Protocol

    IBM Research

  53. LAP: An Agent-to-Instrument Protocol for Autonomous Science

    Jun 2, 2026Linwu Zhu, Liqiang Gao, Yan Chen +2LaboratoryModel Context Protocol

    Shiyanjia Lab

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

    Jun 1, 2026Wenhao Wang, Peizhi Niu, Gongyi Zou +9Personalized Large Language Model AgentsModel Context Protocol

    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

  55. SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning

    Jun 1, 2026Lichao Wang, Zhaoxing Ren, Tianzhuo Yang +4Large Language Model SafetyLLM Defense Mechanisms

    1Beijing Institute of Technology · 2Beijing Academy of Artificial Intelligence · Institute for Artificial Intelligence, Peking University

  56. memorywire: A Vendor-Neutral Wire Format for Agent Memory Operations

    May 31, 2026Thamilvendhan MunirathinamNativememModel Context Protocol

    Independent Researcher

  57. An Organization-Scoped LLM Agent Runtime Architecture for Regulated Cybersecurity Operations

    May 28, 2026George Fatouros, Georgios Makridis, George Kousiouris +2CybersecurityCompliance

    Innov-Acts Ltd Nicosia, Cyprus · Dept. of Digital Systems University of Piraeus Athens, Greece · Dept. of Informatics and Telematics Harokopio University Athens, Greece

  58. mcp-proto-okn: Natural-language access to open scientific knowledge graphs through the Model Context Protocol

    May 28, 2026Peter W. Rose, Benjamin M. Good, Amanda M. Saravia-Butler +7Knowledge GraphsModel Context Protocol

    San Diego Supercomputer Center, University of California San Diego, La Jolla, CA 92093, USA · The Scripps Research Institute, La Jolla, CA 92037, USA · Amentum, Space Biosciences Division, NASA Ames Research Center, Moffett Field, CA 94035, USA +3

  59. Indexing the Unreadable: LLM-Native Recursive Construction and Search of Service Taxonomies

    May 28, 2026Wei Zheng, Yang Yan, Yiyang Shao +6Large Language Model AgentsTaxonomy

    openJiuwen A2X

  60. DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers

    May 27, 2026Aditya Pujara, Xiaogang Zhu, Hsiang-Ting ChenModel Context ProtocolGated Deltanet

    Microsoft · University of Adelaide