Your copy is written in your repo. Your brand belongs there too.
Give every AI agent your brand memory — and a score that proves it landed.
Marketing copy, email text and UI microcopy increasingly get written in the editor, by an agent that does not know your brand. With Branddock in Cursor that agent pulls your brand voice and brand rules before it writes — and you can score a string before you merge it. Your BRAND.md can sit in your repo root alongside it.
Connect in 30 seconds
- Add `branddock.app/mcp` as an MCP server in your Cursor settings.
- Authorise and select your brand.
- Ask for copy, or have an existing string scored against your brand.
Works in any MCP-compatible editor — Cursor, Claude Code, Windsurf.
Try it right away
Paste this prompt once the connection is live. You get copy in your brand voice, with an F-VAL score underneath.
Rewrite the hero copy in `page.tsx` in our brand voice and score the result. Show the old and new versions side by side.
Everyone can write. We show the number.
F-VAL scores every piece 0-100 on brand fidelity across three pillars: style (35%), AI judgement (45%) and brand rules (20%) — with concrete findings attached. Free on every piece, including over the API. No more debating whether something is on brand; there is a number.
Running multiple client brands?
On Agency you manage 15 brands for €349 a month — roughly €23 per client brand. Every brand keeps its own brand DNA, its own voice and its own score, and your agent works in whichever brand you select.
See the agency setup28 dagen gratis · 300 credits · geen creditcard