Launch story: LinkBit
Short links, QR codes, and click analytics as an MCP server — setup for Claude, Cursor, and n8n in under a minute.
Contents
LinkBit is an MCP server for short links, QR codes, and click analytics.
Ask your agent to shorten a campaign URL with UTM tags, generate a print-ready QR, or pull country and device stats — without leaving the chat.
What it does
- Shorten one URL or bulk-create many (
shorten_url/shorten_urls)
- Optional custom slug, note, and
utm_*fields
- List, update, disable, or delete links
- QR as PNG or SVG (
get_qr)
- Per-link and account analytics (
get_link_stats,get_analytics)
Product and docs: linkbit.live · Docs · MCP
Supported agents & runtimes
Any MCP client that can run a local stdio server via npx:
- Claude Code / Claude Desktop
- Cursor
- ChatGPT (MCP-capable clients)
- Codex and other OpenAI agent harnesses with MCP
- n8n (and similar automation hosts that speak MCP or call the same REST API)
Quick start
- Create an API key (
slk_…) at linkbit.live
- Node.js 18+
- Install:
npx -y linkbit-mcp
Claude Code:
claude mcp add linkbit -e APIKEY=YOURAPI_KEY -e APP_URL=https://linkbit.live -- npx -y linkbit-mcp
Cursor / Claude Desktop (mcp.json):
{
"mcpServers": {
"linkbit": {
"command": "npx",
"args": ["-y", "linkbit-mcp"],
"env": {
"APP_URL": "https://linkbit.live",
"API_KEY": "slk_your_key"
}
}
}
}
Try: “Shorten https://example.com/campaign as slug spring with utm\_source newsletter, then show clicks.”
Registry & source
- npm:
linkbit-mcp
If you ship something with LinkBit, tell the author — launch stories like this are how the directory stays useful.
Continue reading
All posts
Launch story: Roomcomm
Codex and other agents from different owners share one room. Every owner reads the same transcript. A room is a link: hand it to your agent, someone hands it to theirs, and they talk.

Why I Don't Let My AI Agent Apply Terraform
agentic-boundary-terraform-skills is a skill for Claude Code, Codex, Cursor and Windsurf. It lets an AI agent work on your Terraform, with deploy credentials kept out of the agent's session.

Why I built GlanceFlow: knowing what Claude Code is doing, at a glance
GlanceFlow puts one calm, plain-English checklist above the Claude Code prompt: the plan, live progress, and a clear signal when Claude needs you.
