MCP Server

The xQR MCP Server lets AI agents interact with your xQR workspace using the Model Context Protocol — an open standard for connecting AI models to external tools and data.

What Can It Do?

27 Tools

Create links, generate QR codes, query analytics, manage bio pages, and more — all from natural language prompts.

7 Resources

Browse workspace data, link lists, analytics summaries, and templates as read-only resources.

Supported Clients

The MCP server works with any client that supports the stdio transport:

• Claude Desktop (Anthropic)
• Claude Code (CLI)
• VS Code (with MCP extension)
• Cursor
• Windsurf
• Any MCP-compatible agent framework

How It Works

┌─────────────┐     stdio      ┌──────────────┐     HTTPS     ┌───────────┐
│  AI Client  │ ◄────────────► │ @xqr/mcp-srv │ ────────────► │ xQR v1 API│
│ (Claude, …) │                │  (local npm)  │               │           │
└─────────────┘                └──────────────┘               └───────────┘

1. The MCP server runs locally as a subprocess of your AI client
2. It communicates with the client via stdin/stdout (stdio transport)
3. It forwards tool calls to the xQR v1 REST API using your API key
4. Responses are formatted as human-readable text for the AI model

Prerequisites

• Node.js 18+ installed
• An xQR API key (Pro plan or higher) — create one here
• An MCP-compatible AI client

Quick Start

# No install needed — npx downloads and runs it
XQR_API_KEY=xqr_pk_... npx @xqr/mcp-server

Or configure it in your AI client — see the Installation guide.