Run any published agent workflow with one HTTP call (and from Claude Code over MCP) Rokha launched a platform that lets developers run published agent workflows with a single HTTP call or from Claude Code over MCP, without installing anything. Workflows, called "rigs," are validated against their published input contract before execution, and runs return a run_id, step-by-step status, output and traces; missing API keys surface as a 409 needs_secret error before any spend. The company says builders are paid based on actual usage rather than posts, with the top 10 Network Members paid in its token. Most agent skills are files in a repo. Nothing happens until something runs them. Rokha is the AI studio and marketplace where they run for real: sandboxed or over remote MCP, no install, and every run leaves a trace you can read back. This post shows how to use it in five minutes, then where we are and where we're going. claude mcp add --transport http rokha https://rokha.ai/mcp/jsonrpc Ask Claude to search the Rokha registry for what you need. Searching needs no account. Running asks you to sign in once through OAuth. A rig is a published workflow. This one audits an X account: curl -X POST https://rokha.ai/api/rigs/run \ -H 'content-type: application/json' \ -d '{"rig":"x-audit","input":"rokha agent"}' You get a run id and a poll block. Without an account you also get an anon session id . Send it back as a header: curl https://rokha.ai/api/rigs/runs/