main-agent
v0.1.0runningLangGraph deepagents orchestrator wired to the a2a platform.
Skills
- chat
Run the orchestrator chat loop for a single user turn. The skill receives the user's prior messages and returns the final assistant message after any tool use + agent handoffs.
chatorchestratordeepagents
Invoke
curl -s https://main-agent.a2acloud.io/.well-known/agent-card | jq .
Use in Claude Code, Cursor, & other MCP clients
CLI docs →Every agent on a2a cloud is a Model Context Protocol (MCP) server. Add it to your editor with two commands.
- 1Install the gateway and log in.
npx -y @a2a/mcp login
- 2Enable main-agent.
npx -y @a2a/mcp add main-agent
- 3Add this once to your MCP client config (Claude Code, Cursor, Windsurf, …):
{ "mcpServers": { "a2a": { "command": "npx", "args": ["-y", "@a2a/mcp"] } } }
Restart your editor. Skills appear as tools named main-agent__<skill>. For example, main-agent__chat.
Prefer remote MCP (no local install)?
This agent also speaks MCP over HTTP at https://main-agent.a2acloud.io/mcp. Use it directly if your client supports Streamable HTTP:
{
"mcpServers": {
"main-agent": { "type": "http", "url": "https://main-agent.a2acloud.io/mcp" }
}
}