A2A, ACP and AG-UI

2 min read
On trails:AGPROTOstep 4/4

MCPMCPModel Context Protocol: one standard way for an agent to reach tools and data.Opens in a new tab covers agent to tool. The other names on the page cover the other two directions: agent to agent (A2A, and ACP before it) and agent to user (AG-UI).

A2A

A2A is for one direction only: agent to agent. It does not try to cover tools or user interfaces, which is why it sits beside MCP and not in place of it. It came from Google and now lives under the Linux Foundation.

A client agent fetches the remote agent's Agent Card from a well-known URL, which lists skills, endpoint and auth. The client picks the agent for the task, sends it a message with SendMessage, and gets back a message or a task to track. client agent remote agent DISCOVER, DESCRIBE GET /.well-known/agent-card.json Agent Card: skills, endpoint, auth picks the agent for the task COMMUNICATE SendMessage Message, or a Task to track
Discover, describe, communicate.

A client agent finds a remote one through its Agent Card: a JSON document, usually served from a well-known path, that lists the agent’s identity, skills, endpoint and the auth it needs. It then sends a message. The remote agent can answer directly, or create a task with its own lifecycle (working, completed, failed, input required) that the client tracks.

The remote agent stays opaque. The two collaborate without the client seeing its internal logic, memory or tools. That is the difference from calling an agent as a tool, which, in the A2A docs’ words, cannot capture its full capabilities.

ACP

ACP, the Agent Communication Protocol, was IBM Research’s agent protocol, started in March 2025 for its BeeAI platform. In August 2025 it was merged into A2A under the Linux Foundation: the ACP team stopped active development and moved its assets and expertise across. Treat ACP as history. The agent-to-agent standard going forward is A2A.

The page lists A2A, A2T, A2E and A2H under ACP, as agent to agent, tools, environment and human. Those names do follow one pattern, A2x, but they are not parts of ACP. A2T is an individual IETF Internet-Draft for listing and invoking tools, now expired. A2H is a Twilio Labs spec for multi-channel approvals from people, and its AUTHORIZE intent is a human in the loopHuman in the loopA pause in the agent's decision, where a person approves before a high-risk action runs.Opens in a new tab check. A2E turns up as Agent-to-Execution, a declarative workflow protocol from an open-source project, not as an environment protocol. All three are young, and none is an established standard.

AG-UI

AG-UI, the Agent-User Interaction protocol, is an open, event-based protocol for connecting agents to user-facing apps. The agent streams its intermediate work, such as chat, tool events and state, to the frontend, and the user’s actions flow back. It grew out of CopilotKit’s work with LangChain and CrewAI.

ProtocolConnectsState
MCPAgent and tool or dataOpen standard, contributed to the Linux Foundation’s Agentic AI Foundation in December 2025.
A2AAgent and agentLinux Foundation project, with ACP merged into it.
ACPAgent and agentDevelopment stopped in 2025. Folded into A2A.
AG-UIAgent and user interfaceOpen protocol that grew out of CopilotKit’s work with LangChain and CrewAI.
Where each protocol sits

Sources