Structured and standardized
Fixed, machine-parseable fields for identity, interfaces, capabilities, skills, and security, defined by the open A2A specification.
Agent Card for Agent2Agent (A2A)
Create, validate, and publish A2A Agent Card JSON for AI agent discovery.
{
"name": "Customer Support Agent",
"description": "A2A agent for support tasks",
"version": "1.0.0",
"supportedInterfaces": [{
"url": "https://api.example.com/a2a",
"protocolBinding": "JSONRPC",
"protocolVersion": "1.0"
}],
"skills": [{ "id": "resolve-support-request", … }]
}What is an Agent Card?
An Agent Card is a standardized JSON document that declares an AI agent's identity, capabilities, skills, and access requirements. It is the README and business Agent Card of the agent era — published at a well-known URL so people and machines can understand what an agent does before calling it.
Readable by humans and machines
One JSON document serves integrators reading documentation and orchestrators routing tasks automatically.
Versioned and dynamic
Agent Cards evolve with the agent: the version field and JWS signatures let clients detect and trust changes.
Explicit boundaries
Authentication requirements and skill limits are declared up front, before any call is made.
Why agents need Agent Cards
Thousands of agents can only find, trust, and delegate to each other when capability descriptions follow one standard.
Discovery and routing
When a task arrives, orchestrators compare Agent Cards to pick the right specialist — no Agent Card, no match.
Trust before invocation
Declared skills, provider identity, and signed Agent Cards reduce the uncertainty of calling a black-box AI service.
Multi-agent collaboration
In an A2A system, one agent reads another's Agent Card to decide whether to hand over a task. The Agent Card is the handshake.
Tools for every part of your Agent Card
Create, inspect, and understand the metadata that makes an A2A Agent Card clear and discoverable.
Agent Card Generator
Create A2A Agent Card JSON from a guided form with endpoint, capabilities, skills, modes, and auth metadata.
Open toolAgent Card Validator
Paste JSON or check a live base URL for required fields, endpoint quality, auth clarity, and discovery readiness.
Open toolAgent Card Examples
Start from practical templates for support, booking, shopping, coding, research, and internal workflow agents.
Open toolSchema Guide
Understand identity, supported interfaces, capabilities, default modes, skills, provider, and security fields.
Open toolWell-known URL Checker
Check both /.well-known/agent.json and /.well-known/agent-card.json for A2A discovery compatibility.
Open toolCore Features of Agent Card Technology
Our Agent Card platform is based on the open Agent2Agent (A2A) protocol initiated by Google and governed by the Linux Foundation's Agentic AI Foundation (AAIF), enabling interoperable communication and collaboration between agents
Agent2Agent Capability Discovery
Through standardized JSON format Agent Cards, agents can automatically discover and invoke capabilities and services of other agents in the Agent2Agent ecosystem.
Agent Card Task Management
Agent Card provides complete task lifecycle management in the Agent2Agent protocol, supporting both simple tasks that can be completed instantly and complex workflows that require long-running operations.
Multi-Modal Agent Card Support
Not limited to text interactions, our Agent Card platform also supports seamless Agent2Agent communication via audio, video, and other media formats.
Agent2Agent Collaboration Capabilities
Using Agent Card technology, agents can share contexts, replies, artifacts, and user instructions, enabling true multi-agent Agent2Agent collaboration scenarios.
Agent Card Security First
Default support for enterprise-grade authentication and authorization mechanisms in Agent Card specifications, ensuring secure and reliable Agent2Agent interactions between agents.
Agent Card User Experience Negotiation
With Agent Card technology, agents can specify content types and formats in the Agent2Agent protocol, ensuring consistency and fluidity of user interfaces and interactive experiences.
Understanding the Agent2Agent (A2A) Protocol and Agent Card
The Agent2Agent protocol and Agent Card specification, initiated by Google and now governed under the Linux Foundation's Agentic AI Foundation (AAIF) alongside 50+ industry partners (with IBM ACP merged into A2A), aims to enable seamless collaboration between intelligent agents across diverse frameworks.
View Agent2Agent (A2A) Specification1
Client Agent in Agent2Agent Protocol - Agent Card enabled client agents are responsible for processing user tasks and communicating them to remote agents using the Agent2Agent protocol
2
Remote Agent in Agent2Agent Protocol - Agent Card compliant remote agents perform actions based on received tasks and return results through the Agent2Agent protocol
3
Agent Card Based on Open Standards - Agent Card and the Agent2Agent protocol are built on existing standards like HTTP and JSON, easy to integrate into existing technology stacks
Agent2Agent Protocol Workflow with Agent Card
- 1
Agent Card Capability Discovery
Agents publish their capabilities in Agent Card JSON format through the Agent2Agent protocol
- 2
Agent2Agent Task Management
Agent Card defines task objects and their lifecycle in the Agent2Agent protocol, supporting real-time feedback and status updates
- 3
Agent2Agent Collaboration & User Experience
Using Agent Card, agents exchange messages, negotiate content types and formats in the Agent2Agent protocol, ensuring a consistent user experience
Who works with Agent Cards
From solo builders to compliance teams, the same document answers different questions.
AI developers
Define, debug, and distribute agents as reusable components with a spec-shaped Agent Card.
Architects and DevOps
Deploy, configure, and monitor agent infrastructure from machine-readable metadata.
Security and compliance
Audit which agents hold which permissions and how data flows, straight from the Agent Cards.
End users
Read the human-friendly view to see what an assistant can do and where its limits are.
Technical Guides
Agent Card Guides & Technical Deep Dives
Practical engineering tutorials, protocol specifications, and security best practices for building production-ready A2A Agent Cards.
Security11 min read
Signed Agent Cards: preventing poisoning and spoofing with JWS
Learn how A2A v1.0 uses JSON Web Signatures (JWS) in the signatures array to protect Agent Cards from tampering, poisoning, and impersonation on open networks.
Architecture10 min read
Unified agent architectures: A2A and MCP in practice under the AAIF
Discover how the Linux Foundation AAIF unifies MCP and A2A into a dual-layer architecture, pairing local tool execution with cross-framework agent discovery.
Ecosystem9 min read
A2A x402 extension: enabling pay-per-call monetisation for AI agents
Learn how A2A x402 brings HTTP 402 Payment Required to Agent Cards, enabling autonomous agents to declare pricing, meter usage, and settle calls in real time.
Frequently Asked Questions about Agent Card and Agent2Agent
Learn more about Agent Card and the Agent2Agent (A2A) protocol
What is Agent Card in the Agent2Agent protocol?
+
Agent Card is a structured data format defined in JSON that describes the capabilities, features, and services of an AI agent. It is the foundation for capability discovery between agents in the Agent2Agent protocol, allowing client agents to find and utilize the most suitable remote agent for completing specific tasks.
How does the Agent2Agent protocol differ from other interoperability protocols?
+
The Agent2Agent (A2A) protocol and Agent Card technology complement protocols like MCP (Model Context Protocol). Both operate under the Linux Foundation's Agentic AI Foundation (AAIF) to form an open dual-layer infrastructure: MCP handles North-South interaction (connecting an agent downwards to tools, APIs, and data), while A2A and Agent Card handle East-West collaboration (connecting independent agents across frameworks and organizations).
Who is involved in developing the Agent2Agent protocol and Agent Card?
+
The Agent2Agent protocol and Agent Card specification were originally initiated by Google and contributed to the Linux Foundation's Agentic AI Foundation (AAIF). Supported by over 50 leading technology companies—including Atlassian, Box, Cohere, Intuit, LangChain, MongoDB, Salesforce, SAP, ServiceNow, and unified with IBM's Agent Communication Protocol (ACP)—it is an open, community-governed standard for agent interoperability.
What are the benefits of using the Agent2Agent protocol with Agent Card?
+
Using the Agent2Agent protocol with Agent Card enables seamless collaboration between agents, increases automation, and creates more coherent user experiences across different systems and applications. It provides businesses with a standardized method for managing agents across multiple platforms, reducing long-term costs and enhancing the functionality and value of agents in the Agent2Agent ecosystem.
What's the difference between Agent2Agent and MCP?
+
Under the Linux Foundation AAIF framework, A2A and MCP form the twin pillars of multi-agent architecture. MCP (Model Context Protocol) connects agents to internal tools, plugins, and data sources (North-South connectivity). A2A (Agent2Agent) uses Agent Cards (agent.json) to enable independent agents to discover each other, negotiate capabilities, authenticate, and collaborate across boundaries (East-West connectivity). They complement each other seamlessly.
Join the Agent2Agent Ecosystem with Agent Card
AgentCard.net provides Agent Card generator, validator, examples, schema guidance, and well-known URL checks for A2A developers.