Introduction
Agent Explorer is a web-based testing and validation tool for the Agent-to-Agent (A2A) protocol. It helps developers build, test, debug, and simulate A2A-compliant agents — all from one interface.
What is A2A?
The Agent-to-Agent (A2A) protocol is an open standard that enables AI agents to communicate with each other. It defines how agents discover each other's capabilities, exchange messages, and coordinate on tasks.
What Agent Explorer Does
Agent Explorer provides a full suite of tools across two main areas:
Testing Real Agents
- AgentCard Discovery & Validation — Fetch and validate agent cards from any A2A-compliant agent
- Payload Builder — Build and test A2A message payloads interactively
- Conversation Testing — Send messages and track multi-turn conversations
- Task State Tracking — Monitor task states and transitions
- Push Notification Webhooks — Receive real-time task updates via webhooks with full delivery observability
- Request/Response Logging — Inspect raw HTTP requests and responses
- OAuth 2.0 Support — Authenticate with secured agents
Building Mock Agents
- Custom Mock Agents — Create fully configurable A2A agents with a multi-step wizard
- Visual Flow Builder — Design response logic using a node-based visual editor
- Simulation Features — Simulate errors, delays, and custom task states
- Skill Routing — Route messages to different response flows by skill (manual, pattern, or LLM-based)
- LLM Integration — Connect OpenAI-compatible models for intelligent mock responses
Collaboration
- Teams — Organise projects and mock agents by team
- Shared Access — Team members (owner, admin, member) share resources
Who Is It For?
Agent Explorer is designed for:
- Agent Developers building A2A-compliant agents
- Integration Engineers connecting systems via A2A
- QA Teams testing agent implementations
- Anyone learning the A2A protocol