ChiefLab in 60 seconds.
Pick one live path — hosted MCP, Cursor one-click, or direct HTTPS. Get a key, fire your first launch. The product is the closed loop: chiefmo_launch_product → user approves on signed reviewUrl → chiefmo_publish_approved_post + chiefmo_send_approved_email → 24h later chiefmo_measure_launch_results.
Step 1 — Get an API key (10 seconds)
One click at chieflab.io/get-key. No email. The page mints a workspace + key for you. Save the clp_dev_… string.
Or, agent-first: have your agent call chieflab_signup_workspace on your behalf. The agent surfaces a single-use delivery URL; you click, copy the key, paste into your agent's config.
Step 2 — Install (pick one path, ~30 seconds)
Hosted MCP (live today)
curl -X POST https://api.chieflab.io/api/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' Cursor (one-click)
Open this cursor:// link.
Paste your key when prompted. Restart Cursor. The chiefmo_* tools appear in your tool picker.
Claude Desktop / Claude Code / any remote-MCP host
Use the hosted MCP URL directly where your host supports remote MCP:
{
"mcpServers": {
"chieflab": {
"url": "https://api.chieflab.io/api/mcp",
"headers": { "Authorization": "Bearer clp_dev_<paste-your-key>" }
}
}
} If your host only supports stdio MCP, install the bridge:
npm install -g @chieflab/mcp-server Direct HTTPS (no install)
curl https://api.chieflab.io/api/mcp \
-H "Authorization: Bearer clp_dev_..." \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"chiefmo_launch_product","arguments":{"productUrl":"yoursite.com","goal":"Get our first 100 users"}}}' Fallback host: if api.chieflab.io ever returns a network error,
you can swap to the brand domain https://chieflab.io/api/mcp — same backend,
routed through Cloudflare. Both surfaces are smoke-checked on every deploy
(scripts/customer-smoke.mjs).
TypeScript SDK / CLI
npx @chieflab/cli init
npm install @chieflab/sdk The CLI plants repo-level agent instructions. The SDK wraps the hosted MCP for app/runtime integrations.
Step 3 — Fire your first launch (~20 seconds)
From HTTPS
curl -X POST https://api.chieflab.io/api/mcp \
-H "Authorization: Bearer $CHIEFLAB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0", "id": 1, "method": "tools/call",
"params": {
"name": "chiefmo_launch_product",
"arguments": {
"productUrl": "https://yoursite.com",
"goal": "Get our first 100 users",
"channels": ["linkedin", "x", "email"]
}
}
}' From inside Cursor / Claude Desktop / Codex
> I just shipped my product at https://yoursite.com.
Use ChiefMO to launch it. The agent picks chiefmo_launch_product automatically (BM25 match on "launch" + the server-level instructions field).
What you get back
{
"launchId": "...",
"launchPack": {
"positioning": { ... }, // source-of-truth paragraph
"channels": {
"linkedin": { body, ... }, // per-channel briefs
"x": { body, ... },
"email": { body, ... }
}
},
"publishActions": [ // approval-gated, persisted
{ id, channel, connector, executorTool: "chiefmo_publish_approved_post",
status: "awaiting_approval", preflight: { ... } }
],
"reviewUrl": "https://chieflab.io/runs/<id>?token=..." // HMAC, 7-day TTL
} Step 4 — Approve in browser → ship
Open the reviewUrl. No login. Read the briefs. Approve each action. Then your agent fires:
# Call each approved action's executorTool via tools/call.
# Example executor names:
# chiefmo_publish_approved_post
# chiefmo_send_approved_email Each fires for real (Zernio for social, Resend for email). Returns the live platform URL / messageId. Read the full closed-loop guide →
Step 5 — 24h later
# 24h later, call:
# chiefmo_measure_launch_results({ "runId": "..." }) Pulls Zernio engagement + GA4 traffic + Search Console queries. Recommends ONE next-iteration change. The cron at /api/cron/tick auto-fires this for every publish that records a launch_followup row, so even if you never call it manually the metrics + recommendation get webhooked back to you (if webhookUrl was set on the launch).
What's next
- The closed loop in depth — every step, every gate, every guarantee
- MCP reference — JSON-RPC contract, all all production tools, error codes
- For AI agents — instruction text agents read at session start
- Open your dashboard — see every run, manage tenants, manage connections