// AGENT PROTOCOLS
The Three Protocols
Standardizing Agent Communication
Open protocols are replacing bespoke integrations. MCP connects agents to tools and data. A2A enables agent-to-agent collaboration. ACP brings REST-native interoperability. Understand all three — and when to use each.
MCP
LIVE
Model Context Protocol
The universal standard for connecting AI models to external data sources and tools.
VendorAnthropic
Released2024
Sections6
READ_EXPLAINER
A2A
LIVE
Agent2Agent Protocol
Open protocol enabling AI agents to discover, communicate, and collaborate with each other.
VendorGoogle
Released2025
Sections6
READ_EXPLAINER
ACP
BETA
Agent Communication Protocol
REST-native protocol for agent-to-agent communication built on OpenAPI standards.
VendorCisco / BeeAI
Released2025
Sections5
READ_EXPLAINER
// QUICK_COMPARISON
MCP vs A2A vs ACP at a Glance
| Aspect | MCP | A2A | ACP |
|---|---|---|---|
| Primary purpose | Agent-to-tool/data connection | Agent-to-agent communication | Agent-to-agent via REST |
| Architecture | Client-server (host-client-server) | Client agent → remote agent | REST endpoints |
| Message format | JSON-RPC 2.0 | JSON-RPC 2.0 over HTTP | HTTP REST / OpenAPI |
| Transport | stdio, Streamable HTTP | HTTP + SSE | HTTP REST |
| Governance | Anthropic (open spec) | Google (open spec) | Cisco / BeeAI (open spec) |
| Released | November 2024 | April 2025 | 2025 |
Each protocol page includes a deeper comparison with additional dimensions. Start with MCP →