Skip to main content
The Model Context Protocol (MCP) is an open protocol for connecting AI assistants (Claude, ChatGPT, Cursor, VS Code Copilot, and others) to external tools and data over a standard JSON-RPC interface. Instead of copy-pasting into a dashboard, you talk to Scanova in plain language from inside the AI tool you already use — “list my active QR codes,” “create a QR code for our new landing page,” “show me last week’s scan analytics.” Scanova runs a real, dedicated MCP server for this — it’s not just an API wrapper glued onto an existing endpoint. The server is open source: github.com/trycon/scanova-mcp.
How this page was verified. The setup flow described here (and in Setup) is read directly from the dashboard’s MCP integration component and its supporting config, not guessed. The tool list in Available tools is read from the actual tools/list handler in the public trycon/scanova-mcp source — not from that repo’s README, which is out of date (it advertises only 7 tools; the deployed server exposes 42). Live screenshots of the setup panel could not be captured this pass — the test account provisioned for this review unexpectedly required passkey MFA with no accessible backup code, which blocked an automated login. Everything below is still verified against real, current source — just not against a live click-through.

What you can do with it

Once connected, your AI assistant can act on your Scanova account through the same Management API the dashboard itself uses. Broadly, that covers:
  • QR codes — create, list, update, retrieve, activate/deactivate, delete, download (PNG/JPG/PDF/SVG/EPS or a print-ready PDF), and restyle an existing QR code’s visual design.
  • Analytics — account-level usage counters, per-QR scan analytics (by device, geography, date), and exporting analytics or raw scan logs.
  • Folders — create, list, rename, delete, and move QR codes between folders.
  • Forms & lead lists — list, inspect, update, and delete lead-capture forms and lead lists, and attach/detach them to a QR code.
  • Users — list, invite, remove, and change the role of users on the account.
  • Scanova’s own docs — a bridge tool lets the assistant search or read this documentation site live while it works, so it can look up something like the pattern-info schema before calling another tool.
See Available tools for the complete, per-tool list with descriptions.

Where it lives

In the dashboard, go to Integrations and open the Model Context Protocol card (category: Workflow). This opens a setup panel with your server URL, per-AI-tool connection steps, and a token fallback for clients that don’t support OAuth — see Setup for the full walkthrough.

Access requirements

The MCP integration is gated behind an entitlement quota codename, INTEGRATION_MCP, checked on both the dashboard card (to show Connect instead of Upgrade) and on every request the MCP server makes to the Management API on your behalf. This is an admin/plan-managed grant rather than a quota you turn on yourself.
Don’t treat any specific plan-tier name as confirmed here. The frontend’s own quota-to-plan mapping table carries an explicit maintainer comment stating its plan-tier values are unverified placeholders (not sourced from the real plans table), so a claim like “MCP requires the Pro plan” cannot be confirmed from the code alone. What’s confirmed: this is gated by the INTEGRATION_MCP codename specifically (distinct from the general MANAGEMENT_API quota that the plain Management API uses), and a Pro-plan account used for this review needed that codename granted directly before the integration unlocked. If your account shows Upgrade on the MCP card, contact support@scanova.io.

Setup

Generate a connection, and wire it into Claude, ChatGPT, Perplexity, or a config-file-based client.

Available tools

The full, verified list of every tool the server exposes.
  • MCP setup — connect Claude, ChatGPT, Perplexity, or a config-file client to the server described here.
  • Available tools — the complete, per-tool reference for everything the server exposes.
  • Management API overview — the environment=mcp token type and its INTEGRATION_MCP quota gate, documented in full.