Skip to main content

Quick start

Connect an AI assistant to Zivaro Launch with one URL, or call the REST API from your code.

MCP server URL: https://zivarolaunch.com/mcp

Claude (claude.ai and Claude Desktop)

  1. Open Settings, then Connectors, and choose to add a custom connector.
  2. Name it Zivaro Launch and paste https://zivarolaunch.com/mcp as the URL.
  3. Ask Claude to search Zivaro Launch. The first time it needs your account, Claude opens a sign-in page here; choose Allow access.

Claude Code

claude mcp add --transport http zivarolaunch https://zivarolaunch.com/mcp

Then run /mcp in Claude Code to sign in when a tool asks for your account.

ChatGPT

  1. In ChatGPT settings, open Connectors (developer mode may need to be switched on for custom connectors).
  2. Create a connector with the URL https://zivarolaunch.com/mcp and OAuth sign-in.
  3. Use it in a chat; ChatGPT sends you here to allow access the first time.

Cursor

Add this to ~/.cursor/mcp.json (or .cursor/mcp.json in a project):

{
  "mcpServers": {
    "zivarolaunch": {
      "url": "https://zivarolaunch.com/mcp"
    }
  }
}

VS Code

Add this to .vscode/mcp.json in your workspace, then start the server from the MCP view:

{
  "servers": {
    "zivarolaunch": {
      "type": "http",
      "url": "https://zivarolaunch.com/mcp"
    }
  }
}

Any other MCP client

Use the Streamable HTTP transport with https://zivarolaunch.com/mcp. Protocol versions 2026-07-28 and the earlier initialize-based versions (2025-03-26 to 2025-11-25) are supported. Sign-in follows the MCP authorization spec: protected resource metadata at /.well-known/oauth-protected-resource/mcp, OAuth 2.1 with PKCE, client ID metadata documents or dynamic registration. Test it with the official MCP Inspector: npx @modelcontextprotocol/inspector.

REST with curl

curl "https://zivarolaunch.com/api/v1/listings?q=invoicing&per_page=5"
curl "https://zivarolaunch.com/api/v1/leaderboards/community-weekly"

With your account (create a key under API keys):

export API_KEY=lk_...
curl -X POST "https://zivarolaunch.com/api/v1/drafts" \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"url": "https://example.com"}'

Python

import os, time, requests

API = "https://zivarolaunch.com/api/v1"
H = {"Authorization": f"Bearer {os.environ['API_KEY']}"}

draft = requests.post(f"{API}/drafts", json={"url": "https://example.com"}, headers=H).json()
while draft["status"] in ("crawling", "drafting"):
    time.sleep(4)
    draft = requests.get(f"{API}/drafts/{draft['id']}", headers=H).json()
listing = requests.post(f"{API}/drafts/{draft['id']}/submit", headers=H).json()
order = requests.post(f"{API}/orders/checkout", headers={**H, "Idempotency-Key": "my-first-launch"},
                      json={"items": [{"product": "launch", "listing_id": listing["listing_id"]}]}).json()
print("Pay here:", order["checkout_url"])

JavaScript

const API = "https://zivarolaunch.com/api/v1";
const res = await fetch(`${API}/listings?q=${encodeURIComponent("ai writing")}`);
const { items } = await res.json();
for (const l of items) console.log(l.name, l.url, l.votes);
Help centre