MCP and A2A under the same roof: for the first time, agents can talk to each other without depending on any single vendor
On August 20, 2026, Google formally transferred the A2A protocol to the Agentic AI Foundation (AAIF) — the same foundation that already hosts Anthropic's MCP. For the first time, the two standards that define how agents connect to tools and how they coordinate with each other share neutral governance, backed by over 250 organizations. Closing that gap isn't a PR move: it's the missing piece for companies building agents that work together without vendor lock-in.
On August 20, 2026, Google formally transferred its Agent2Agent (A2A) protocol to the Agentic AI Foundation (AAIF), the Linux Foundation-directed body that since December 2025 has also hosted Anthropic's Model Context Protocol (MCP). For the first time, the two standards that define the architecture of modern agents share neutral governance. It isn't a code change — it's a structural shift in the ecosystem: agents built by different vendors can now coordinate and share tools following protocols that no single vendor controls unilaterally.
What MCP is, what A2A is, and why having them together matters
The two protocols operate at distinct, complementary layers. MCP (Model Context Protocol) defines how an agent connects to external tools, data, and services — the vertical layer: the agent reaching toward sources of information and action. A2A (Agent2Agent) defines how one agent communicates with another — the horizontal layer: coordination between agents from different systems, different companies, different models. Before August 20, MCP sat under AAIF's governance and A2A was still a Google initiative. Today both layers share the same neutral roof. An agent built on Claude that needs to coordinate with one built on GPT-5 or Gemini can do so following a standard that neither vendor controls unilaterally.
What changes for a company building collaborative agents
- Agentic infrastructure lock-in is no longer inevitable: with MCP and A2A under neutral governance, building on one model or platform doesn't close the door to integrating agents from another vendor — the communication standard is shared.
- Agents can transfer context to each other in a structured way: A2A defines how one agent hands work to another with the context needed to continue — without both needing to run on the same platform or share the same model.
- The risk of betting on the “wrong” protocol disappears: with 250+ organizations — including every major cloud provider — backing the same foundation, choosing MCP or A2A is no longer picking a side: it's adopting market infrastructure.
- Certification and auditing become clearer: protocols under neutral governance have versioned specs, documentation, and predictable change processes — exactly what security and compliance teams need to approve production deployments.