A2A protocol
Rightbrain supports A2A (Agent-to-Agent), Google’s open protocol for interoperability between AI agents. A2A lets an agent built on one framework call an agent built on another, without a custom integration on either side. When you expose a Rightbrain task over A2A, other agent frameworks can invoke it as if it were one of their own agents.
A2A shipped in January 2026 and is new. This page documents what is confirmed by the platform today and flags the details that are still being finalized.
A2A vs MCP
Rightbrain speaks two interop protocols. They target different callers:
If you are wiring a task into a coding assistant or chat client, use MCP. If you are building a multi-agent system where agents hand work to each other, use A2A.
Expose a task over A2A
A task is exposed to A2A when its exposed_to_agents flag is set. Once enabled, the task is served over JSON-RPC at the project-scoped A2A endpoint:
Two discovery endpoints let A2A clients find your agents: GET .../a2a/agents lists every task in the project exposed to agents, and GET .../a2a/agents/{agent_id}/.well-known/agent-card returns the standard A2A agent card for one of them. Requests are then sent to the per-agent JSON-RPC endpoint at POST .../a2a/agents/{agent_id}.
External agent frameworks that support A2A can then discover the task’s capabilities and send it requests over JSON-RPC. The task runs on Rightbrain with its configured model, prompt, and output schema, and returns a structured result to the calling agent.
The dashboard toggle location for exposed_to_agents, the JSON-RPC method surface, and the agent-card discovery path are not yet documented here. Check the API Reference and the dashboard for the current controls before building against them.