LaunchOn.it

npx add-mcp 'https://launchon.it/api/mcp'

title: "MCP Server for AI Agents"
canonical: "https://launchon.it/mcp"

Official MCP server

MCP Server for AI Agents

Search launched products, weekly leaderboards and open launch slots, or draft a launch for founder review. Works from Claude, Cursor or any MCP client. No API key, no install.

Connect your agentGitHub

launchon.it/api/mcp

Public tools

6

Typed JSON-RPC tools

API key

None

Anonymous reading and drafting

Access

Read + Draft

No silent publishes or charges

Transport

HTTP

Streamable, stateless JSON-RPC 2.0

Add LaunchOnIt to your AI client

Nothing to install or build. Paste the remote endpoint into your tool and you're connected.

Claude Code

Run once in your project terminalterminal

claude mcp add --transport http launchonit https://launchon.it/api/mcp

Claude Desktop & Web

Settings > Connectors > Add custom connectorconnector URL

https://launchon.it/api/mcp

Cursor

Add to ~/.cursor/mcp.jsonmcp.json

{
  "mcpServers": {
    "launchonit": {
      "url": "https://launchon.it/api/mcp"
    }
  }
}

VS Code

Add to .vscode/mcp.json in workspace.vscode/mcp.json

{
  "servers": {
    "launchonit": {
      "type": "http",
      "url": "https://launchon.it/api/mcp"
    }
  }
}

6 tools, zero authentication

Five read-only tools and one that drafts. The schemas and limits below match tools/list exactly.

search_products

Read only

Keyword search across every product that has launched on LaunchOnIt. Matches name, tagline and description, ordered strictly by community upvotes. Paid launch tiers determine scheduling timing only and do not affect search ranking.

Argsquery (required) · limit 1-25 (default 10)

get_weekly_leaderboard

Read only

Ranked products for one ISO week, ordered strictly by community upvotes. Paid launch tiers determine scheduling timing only and do not affect leaderboard rankings. Defaults to the live week, which closes Sunday 23:59 UTC.

Argsweek YYYY-Www (optional) · limit 1-50 (default 20)

get_product

Read only

Full public listing for one product: tagline, description, who it's for, the problem it solves, pricing, tech stack, links and upvotes.

Argsslug (required)

get_winners

Read only

Top 3 podium finishers from recent weeks, newest week first. These are the Hall of Fame entries on /winners.

Argsweeks 1-26 (default 4)

get_launch_calendar

Read only

Free launch slots left in the live week and the weeks after it, plus the launch plans and prices. Use it to tell a maker when they would launch.

Argsweeks 1-12 (default 4)

submit_product

Drafts only

Starts a launch for a product URL. LaunchOnIt reads the site, drafts the listing (name, tagline, description, story, pricing, categories) and returns a private review link. The maker opens the link, signs in, edits and publishes. Nothing goes live and nothing is charged from this call.

Argsurl (required) · title · tagline · description · pricing_type (optional overrides)

How submit_product works

Your agent writes the copy. You keep the publish button and the card.

From chat to a launch draft

1. 1

   You ask your agent

   "Launch my product https://example.com on LaunchOnIt." Your agent calls submit_product with the URL.

2. 2

   LaunchOnIt drafts it

   LaunchOnIt reads your website, extracts copy, and drafts the name, tagline, description, story, pricing, and category tags.

3. 3

   You review and publish

   The agent hands you a private review link. Sign in to your dashboard, fine-tune the story, pick a plan, and publish when ready.

An agent can never publish, pay or pick a launch week for you. Drafts stay private behind 192-bit review tokens and expire after 7 days if nobody claims them.

Where to connect

Point your MCP client at the HTTP transport. The discovery files let crawlers find the tools on their own.

Endpoints

MCP Transport POST JSON-RPC 2.0 messages. GET returns discovery info. /api/mcp

MCP Discovery Streamable HTTP manifest describing tool capabilities. /.well-known/mcp.json

Server Card Single-file machine manifest with full schemas and transport metadata. /.well-known/mcp/server-card.json

JSON-RPC 2.0 over HTTP

Stateless request and response. Post one JSON-RPC message (or a batch) and get plain JSON back.

initialize

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "initialize",
  "params": {
    "protocolVersion": "2025-06-18",
    "capabilities": {},
    "clientInfo": {
      "name": "my-assistant",
      "version": "1.0.0"
    }
  }
}

tools/call: search_products

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "search_products",
    "arguments": {
      "query": "ai analytics",
      "limit": 5
    }
  }
}

cURL

curl -s https://launchon.it/api/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_launch_calendar","arguments":{"weeks":4}}}'

Other AI and developer surfaces

MCP is one way in. Use the lightest one that answers your question.

Agent surfaces

GitHub Repository Open-source MCP server implementation, CLI, and schemas

llms.txt Compact site map and docs index for AI agents

llms-full.txt Complete text of all live products, articles, and guidelines

ai.txt Machine-readable permissions for AI crawlers

Markdown Twins Clean markdown for any product: /products/{slug}.md

RSS Feed Live feed of newly launched indie startups

Frequently asked questions

Do I need an API key?

No. Every tool works without an API key. Data queries are completely anonymous, and submit_product creates a private draft that you claim via magic link or OAuth in your dashboard, so no account credentials ever touch your agent.

Can an agent publish or pay for a launch?

No. submit_product only creates a private draft and returns a claim link. Picking a plan, choosing a launch week, and payment all happen securely in your browser once signed in. Unclaimed drafts remain completely private and expire in 7 days.

Should my agent scrape HTML instead?

Please don't. The MCP endpoint returns structured, typed JSON, and every public listing has a lightweight markdown twin at /products/{slug}.md. Both methods are significantly faster, use less bandwidth, and never break from DOM changes.

What rate limits are enforced?

60 requests per minute per IP for general queries, and 5 submit_product draft creations per hour. This is ample headroom for regular developer workflows and automated assistant tasks.

What tools should an agent call first?

Start by reading /llms.txt or calling get_launch_calendar to see which launch weeks still have open slots. Use search_products and get_product to research competitors, or submit_product to draft a launch for review.

---

Prefer citing https://launchon.it/mcp.