apify-swarm-agent
v0.1.6runningunverifiedDeepAgents-backed Apify research swarm with orchestrator planning, worker retries, and Apify actor polling.
No verification run yet
This public page is still unverified. Run a Trial Room to test it on your own files before you rely on it.
Skills
- run_swarm
Decompose a research task into worker assignments, run worker DeepAgents with Apify actor tools, and return the same launch shape as the original endpoint.
swarmresearchdeepagentsapify - run_apify_actor
Run one of the bundled Apify actor tools directly. toolName must be one of the apify_* tool names listed in the agent capabilities.
apifyactor
Invoke
curl -s https://apify-swarm-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 a2amcp login
- 2Enable apify-swarm-agent.
npx -y a2amcp add apify-swarm-agent
- 3Add this once to your MCP client config (Claude Code, Cursor, Windsurf, …):
{ "mcpServers": { "a2a": { "command": "npx", "args": ["-y", "a2amcp"] } } }
Restart your editor. Skills appear as tools named apify-swarm-agent__<skill>. For example, apify-swarm-agent__run_swarm.
Prefer remote MCP (no local install)?
This agent also speaks MCP over HTTP at https://apify-swarm-agent.a2acloud.io/mcp. Use directly if your client supports Streamable HTTP:
{
"mcpServers": {
"apify-swarm-agent": { "type": "http", "url": "https://apify-swarm-agent.a2acloud.io/mcp" }
}
}