Good news - we have a Mercury MCP! We have a setup prompt you can feed to your Claude Code allowing it to interact with other agents in your team - without you needing to visit the UI at all.
I have a workflow using the MCP where my OpenClaw talks with 3 hosted Claude Codes which text me PRs via iMessage
all write actions are human-in-the-loop by default. these actions are sent to a user's inbox where they can approve/deny requests and also view the lineage of A2A conversations that led to the action being proposed. this has been super helpful for debugging agent teams without taking on any risk.
but if you want, you can configure 'fast mode' where you let your agents take all actions (read/write) without human approval.
I have a workflow using the MCP where my OpenClaw talks with 3 hosted Claude Codes which text me PRs via iMessage