REVIEW 30 cited by
A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
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.
Forward citations
Cited by 30 Pith papers
-
Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent
Format effects on multi-hop LLM relay fidelity are tier-dependent: strong relays are nearly lossless, weak relays pay an encoding toll that fixed-key JSON later resists, and structure localizes rather than corrects errors.
-
Networked Intelligence: Active Shared Context Graphs for Human-AI Team Science
A shared 'active context graph' that routes findings among human experts and AI agents surfaced more actionable scientific artifacts in a multi-omics campaign than a standalone AI agent given the same data.
-
A Residual-Shell-Based Lower Bound for Ollivier-Ricci Curvature
A residual-shell construction yields a tighter, still-efficient lower bound on Ollivier–Ricci curvature for 1-hop and k-hop random walks, with reported tens-of-times speedups.
-
Combating Data Laundering in LLM Training
Data laundering collapses original-query memorization detectors; SDR recovers useful detection signals by synthesizing training-like rewrites of proprietary data via a goal-details search.
-
Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy
MCP server faults form five empirical categories—server setting, server/tool configuration, server/host configuration, documentation, and general programming—confirmed by a 41-practitioner survey.
-
Rethinking Query Optimization for Multi-Agent Systems [Vision]
Agentic data pipelines are built by hand today; this paper sets a research agenda for automatically optimizing their structure, model choices, and execution engines jointly as a new query-optimization problem.
-
From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the Web of Agents
The paper organizes Multi-Agent Systems, the Semantic Web, and LLM-based agents into one narrative in which the location of semantic effort migrated from platform, to data, to model.
-
Bridging AI and Software Security: A Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms
Function Calling and MCP architectures show distinct vulnerability patterns, with chained attacks succeeding 91-96% of the time in both.
-
Agentic IoT: Architectures, Applications, and Challenges Toward the Internet of Agents
Agentic IoT is formalized as a cognitive IoT paradigm that embeds LLM-driven agents with perception-reasoning-planning-action-learning loops into cyber-physical systems across the device-edge-fog-cloud continuum.
-
AI Tool Discovery at Scale: All You Need is DNS
ToolDNS repurposes DNS names and EDNS0 payloads to perform hierarchical semantic tool discovery with O(log N) name resolutions and a reported 95.26% search-space reduction.
-
Internet 3.0: Architecture for a Web-of-Agents with it's Algorithm for Ranking Agents
AgentRank-UC ranks agents by mixing usage frequency and measured competence through two PageRank-style equations, and DOVIS defines the telemetry protocol that feeds it.
-
We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems
MCP-powered LLM agents are vulnerable to prompt injection from third-party services, and simple detection or filtering defenses do not reliably stop these attacks.
-
Towards Humanoid Robot Autonomy: A Dynamic Architecture Integrating Continuous thought Machines (CTM) and Model Context Protocol (MCP)
A proposed CTM-MCP architecture for humanoid robot autonomy is supported only by self-assessed LLM simulations, not by real robots or independent benchmarks.
-
The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy
Medical agents should be scaled mainly by richer clinical environments and self-evolution loops, not parameter growth alone, under a three-level autonomy taxonomy.
-
Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directions
A survey proposing a five-dimensional taxonomy of trust crises in open AI agent networks and analyzing blockchain's role as a shared trust infrastructure.
-
AI Agent Communications in AI-Native 6G Network: Status, Challenges and Opportunities
A gap analysis showing that today's AI-native 6G specifications do not yet provide the semantic slicing, cross-layer orchestration, decentralized trust, and protocol adaptation that large-scale AI-agent communication ...
-
Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey
A survey proposing zero-trust architecture for multi-LLM systems in edge computing, with a taxonomy of model- and system-level defenses and a conceptual framework.
-
SDEC: Semantic Deep Embedded Clustering
SDEC is described as a hybrid autoencoder and transformer embedding method that reportedly sets text clustering benchmarks, but the submission's body is a different, unrelated paper.
-
Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling
ToolRegistry unifies LLM tool integration across Python, MCP, OpenAPI, and LangChain, claiming 60-80% less code and up to 3.1x faster concurrent execution.
-
ToolRegistry: A Protocol-Agnostic Tool Management Library for Function-Calling LLMs
ToolRegistry unifies LLM tool registration and execution across four protocols via an RPC-style Tool object, reporting large code reductions and concurrency speedups.
-
Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead
A literature review organizes LLM development into a six-phase software engineering lifecycle and identifies challenges and research directions for each phase.
-
Enhancing Clinical Decision Support and EHR Insights through LLMs and the Model Context Protocol: An Open-Source MCP-FHIR Framework
An MCP-FHIR agent framework for LLM-based EHR summarization and persona-specific explanations is presented, with a qualitative use case on synthetic data.
-
A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control
The authors propose a zero-trust identity and access management framework for AI agents that combines decentralized identifiers, verifiable credentials, a capability-aware naming service, and a global session revocati...
-
Position: Collaborative Agentic AI Needs Interoperability Across Ecosystems
A position paper proposing minimal web-based standards, the Web of Agents, to prevent fragmentation in collaborative agentic AI ecosystems.
-
Securing Agentic AI: From Per-Action Checks to Trajectory Assurance
A vision paper organizing agentic AI security into eleven research directions, with the thesis that safety requires verifiable trajectory-level behavioral guarantees, not per-action checks.
-
Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM Pipelines
The paper proposes a security layer that signs, freshness-checks, policy-validates, and Merkle-logs MCP tool-use manifests before LLM execution, reporting near-linear scaling and low overhead.
-
{\mu}ACP: A Formal Calculus for Expressive, Resource-Constrained Agent Communication
A four-verb calculus claims to encode all finite-state FIPA protocols with near-optimal messages and consensus support, but the proofs are sketched and the real expressive load sits in TLV options, not the verbs.
-
The Trust Fabric: Decentralized Interoperability and Economic Coordination for the Agentic Web
The paper presents a five-layer decentralized framework (Nanda) for agent discovery, trust scoring, and micropayments, but supports its deployment claims only with self-referential descriptions.
-
Why do AI agents communicate in human language?
The paper argues that natural language is structurally mismatched to LLM internal representations, so future AI agents should abandon it for inter-agent communication and train models with structured communication primitives.
-
From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications
This paper is a broad tutorial on applying LAMs and agentic AI to 6G, largely restating existing research rather than introducing new results.
Discussion (0). Continue with ORCID to comment.