Deploy an app from Claude Code in 60 seconds — no dashboard, no CAPTCHA

Openpouch, a new deployment tool created by developer Alex K., enables AI coding agents like Claude Code to deploy applications in under 60 seconds without requiring a dashboard, account, or CAPTCHA. The tool exposes a CLI and MCP server with 13 tools for the full deploy lifecycle, including deploy, verify, logs, inspect, and rollback, while deliberately omitting an approve tool to keep production deployments human-only. Openpouch builds apps on deploy, health-checks them, and outputs structured JSON for agent decision-making, supporting self-repair loops via logs.

Note:I'm the maker of openpouch. This is a how-to, written honestly — it's a technical preview and I'll be clear about the limits. Feedback very welcome. Your coding agent can write the app. It can write the tests. Then it hits deploy — and the cloud asks it to click a fire hydrant. That's the thing nobody designed for: every deploy target assumes a human at a browser. CAPTCHAs, "verify you're human", dashboard-only toggles, OAuth flows that dead-end in a headless tab. An agent that can ship software can't get past a bot-wall built to stop bots. openpouch https://openpouch.dev is the opposite of that: one command to a live URL, no account, no dashboard, no human-verification step anywhere. It ships as a CLI and an MCP server, so it drops into Claude Code or Cursor, Codex, OpenClaw, … as native tools. Here's the 60-second version from Claude Code. claude mcp add openpouch -- npx -y @openpouch/mcp That's it — a zero-dependency stdio MCP server, pulled on demand via npx . It exposes the full deploy lifecycle as 13 tools openpouch deploy , openpouch verify , openpouch logs , openpouch inspect , openpouch rollback , openpouch list , … . There is deliberately no approve tool — approving a production deploy is human-only, in every harness. An agent literally cannot approve its own prod deploy. Previews, though, it just ships. Can't attach MCP servers mid-session? You can prove the whole toolset from any plain shell — the recipe is in the docs https://openpouch.dev/docs/MCP.md . Or skip MCP entirely and use the CLI npx openpouch deploy , same functions, --json + exit codes . Point Claude Code at any app folder and ask it to deploy. Under the hood it calls one tool: // openpouch deploy { "dir": "." } For a full-stack app an API behind the frontend , add a health path so the agent proves the backend is actually up, not just the shell: // openpouch deploy { "dir": ".", "healthPath": "/api/health" } openpouch builds the app on deploy a raw Vite/React/Svelte source folder or a Node server with a build step — no local build needed , starts it in a hardened container, and health-checks it before telling you it's live. The result is structured JSON — exactly what an agent needs to make a decision, plus a plain-language line for the human running it: { "ok": true, "url": "https://your-app-x1y2z3.openpouch.sh", // the shareable link "healthStatus": "healthy", "summary": "Your app is live at https://… — anyone you share it with can open it right away.", "nextCommands": { "verify": "…", "logs": "…", "inspect": "…" }, "evidence": "deploy.manifest.json", "deploy.evidence.json", "DEPLOYMENT.md", "…" } Three things worth calling out: summary DEPLOYMENT.md , deploy.evidence.json , … . After a context reset, a fresh agent re-reads those files and knows exactly what's deployed, where, and how to resume. No hidden state.If the app comes back unhealthy, openpouch logs shows the captured install/build/app output tagged install / build / app — the agent reads the cause, fixes it, redeploys, verifies. A real self-repair loop. --var / --env-file , injected at runtime, reported by name only , but they're ephemeral — no persistent storage yet. npx openpouch deploy Open source, Apache-2.0: github.com/openpouch/openpouch https://github.com/openpouch/openpouch · docs for you and your agent : openpouch.dev https://openpouch.dev If your agent can write software, it should be able to ship it. That's the whole idea.