mlsanityData to 14 Oct 2026

A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)

arXiv 2505.02279 ↗First posted 4 May 2025cs.AIcited by 101

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Large language model powered autonomous agents demand robust, standardized protocols to integrate tools, share contextual data, and coordinate tasks across heterogeneous systems. Ad-hoc integrations are difficult to scale, secure, and generalize across domains. This survey examines four emerging agent communication protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP), each addressing interoperability in deployment contexts. MCP provides a JSON-RPC client-server interface for secure tool invocation and typed data exchange. ACP defines a general-purpose communication protocol over RESTful HTTP, supporting MIME-typed multipart messages and synchronous and asynchronous interactions. Its lightweight and runtime-independent design enables scalable agent invocation, while features like session management, message routing, and integration with role-based and decentralized identifiers (DIDs). A2A enables peer-to-peer task delegation using capability-based Agent Cards, supporting secure and scalable collaboration across enterprise agent workflows. ANP supports open network agent discovery and secure collaboration using W3C decentralized identifiers DIDs and JSON-LD graphs. The protocols are compared across multiple dimensions, including interaction modes, discovery mechanisms, communication patterns, and security models. Based on the comparative analysis, a phased adoption roadmap is proposed: beginning with MCP for tool access, followed by ACP for structured, multimodal messaging session-aware interaction and both online and offline agent discovery across scalable, HTTP-based deployments A2A for collaborative task execution, and extending to ANP for decentralized agent marketplaces. This work provides a comprehensive foundation for designing secure, interoperable, and scalable ecosystems of LLM-powered agents.

Key facts. Cited by 101 papers in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 13 of its 43 references that are in the map. First posted on arXiv 4 May 2025.

Builds on

13 of 43 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Red-Teaming LLM Multi-Agent Systems via Communication Attacks20 Feb
  2. 2025Firewalls to Secure Dynamic LLM Agentic Networks3 Feb

Other references · 11

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  5. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  7. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  8. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
  9. 2023Augmented Language Models: a Surveycited by 403
  10. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systemscited by 62
  11. 2025ToolFuzz -- Automated Agent Tool Testingcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 53; 2026: 48.

101 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  2. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 74
  3. 2025From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflowscited by 58
  4. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 57
  5. 2025LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directionscited by 50
  6. 2025LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?cited by 48
  7. 2025AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocolcited by 39
  8. 2025OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agentscited by 29
  9. 2025A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Controlcited by 28
  10. 2025We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systemscited by 27
  11. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 26
  12. 2025Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interactioncited by 19
38 more
  1. 2025LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queriescited by 17
  2. 2025Agentic AI Frameworks: Architectures, Protocols, and Design Challengescited by 16
  3. 2025Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystemcited by 16
  4. 2026Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANPcited by 15
  5. 2025An Empirical Study of Agent Developer Practices in AI Agent Frameworkscited by 14
  6. 2026Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agentscited by 14
  7. 2025AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysiscited by 13
  8. 2025A Measurement Study of Model Context Protocol Ecosystemcited by 13
  9. 2025The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperationcited by 13
  10. 2026Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundariescited by 13
  11. 2025SoK: Trust-Authorization Mismatch in LLM Agent Interactionscited by 11
  12. 2025The 2025 Foundation Model Transparency Indexcited by 11
  13. 2026SEAGym: An Evaluation Environment for Self-Evolving LLM Agentscited by 11
  14. 2025Trustless Autonomy: Understanding Motivations, Benefits, and Governance Dilemmas in Self-Sovereign Decentralized AI Agentscited by 10
  15. 2025Security Analysis of Agentic AI Communication Protocols: A Comparative Evaluationcited by 9
  16. 2025MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool Usecited by 9
  17. 2025Position: Collaborative Agentic AI Needs Interoperability Across Ecosystemscited by 8
  18. 2025Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigmscited by 7
  19. 2025From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the Web of Agentscited by 7
  20. 2025ACPs: Agent Collaboration Protocols for the Internet of Agentscited by 6
  21. 2025From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systemscited by 6
  22. 2025AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agentscited by 6
  23. 2025Agentic Services Computingcited by 6
  24. 2025ProtocolBench: Which LLM MultiAgent Protocol to Choose?cited by 6
  25. 2025UFO3: Weaving the Digital Agent Galaxycited by 6
  26. 2026Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomycited by 6
  27. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
  28. 2025Enhancing Clinical Decision Support and EHR Insights through LLMs and the Model Context Protocol: An Open-Source MCP-FHIR Frameworkcited by 5
  29. 2025ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMscited by 5
  30. 2025Evolution of AI Agent Registry Solutions: Centralized, Enterprise, and Distributed Approachescited by 4
  31. 2025Agentic Additive Manufacturing Alloy Evaluationcited by 4
  32. 2026Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanismscited by 4
  33. 2026MasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architecturescited by 4
  34. 2025The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Webcited by 3
  35. 2025Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Callingcited by 3
  36. 2026Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agentscited by 3
  37. 2026MCPShield: A Security Cognition Layer for Adaptive Trust Calibration in Model Context Protocol Agentscited by 3
  38. 2026AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agentscited by 3

50 most cited of 101 All 101 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Context Sharing: A Unified Agent Communication Protocol (ACP) for Secure, Federated, and Autonomous Agent-to-Agent (A2A) Orchestration
  2. 2025From Glue-Code to Protocols: A Critical Analysis of A2A and MCP Integration for Scalable Agent Systems
  3. 2025A Study on the MCP x A2A Framework for Enhancing Interoperability of LLM-based Autonomous Agents
  4. 2026AgentRFC: Security Design Principles and Conformance Testing for Agent Protocols
  5. 2025Agent Network Protocol Technical White Paper
  6. 2026Governance Gaps in Agent Interoperability Protocols: What MCP, A2A, and ACP Cannot Express
  7. 2026AIP: Agent Identity Protocol for Verifiable Delegation Across MCP and A2A
  8. 2025MCPZoo: A Large-Scale Dataset of Runnable Model Context Protocol Servers for AI Agent