User Guide

Got an idea? This coach turns it into a full product design through conversation. Paste → log in → start — that's the flow.

Quick start — first session

  1. Connect — On the home Connect section, pick your tool's tab and paste the prompt to your agent.
  2. Log in — Once in the browser with Google/GitHub. (lasts 30 days)
  3. Start — /purpleprint:start (or natural language “start PurplePrint” → pp_start). When the welcome shows, reply “let's start” and Phase 0 begins.

Already have writing·notes·Notion? Paste them in too — it pulls the core and backfills what's missing.

Here's how the first conversation flows:

First session

It's a demo — the real thing runs on your idea, inside your tool. Stuck? Just say “again” or “simpler” and it fixes course.

Connect your tool

Our server is remote HTTP MCP + OAuth. No API keys, no config secrets — pick your tool and paste the prompt to your agent, and it registers itself and walks you through login. One login lasts 30 days.

ToolStatusHow
Claude CodeSupportedURL + alwaysLoad: true + /mcp Authenticate
Cursor · VS CodeComing soonurl in user settings + browser OAuth
CodexComing sooncodex mcp add/login + natural-language pp_*
Windsurf · Antigravity · Lovable · EmergentExploringurl-based + DCR OAuth (validating)

Pick your tool, paste, done

Pick your tool's tab and paste the prompt straight to your agent. It registers and walks you through login.

Add the PurplePrint MCP to Claude Code. Server name: purpleprint, transport: http, URL: https://purpleprint-mcp.purpleprintai.workers.dev/mcp. Register it globally (user scope), and add alwaysLoad: true to mcpServers.purpleprint in ~/.claude.json (this prevents /purpleprint:* slash commands from going missing in recent Claude Code IDE). If editing the file directly, save as UTF-8 no BOM. Walk me through Authenticate in /mcp, and when done confirm that /purpleprint:start shows up.
Add the PurplePrint MCP to this editor. Server name: purpleprint, URL: https://purpleprint-mcp.purpleprintai.workers.dev/mcp. Register it as a remote/http MCP in this tool's settings — globally (user settings, e.g. ~/.cursor/mcp.json or VS Code user settings), not just one project. If an OAuth/authorize flow is needed, walk me through the browser login. If commands don't show up, restart the editor or open a new chat/thread and check again.
Add the PurplePrint MCP to Codex. Server name: purpleprint, URL: https://purpleprint-mcp.purpleprintai.workers.dev/mcp. Register it as a streamable HTTP MCP in ~/.codex/config.toml (shared by Codex CLI/IDE) and complete the OAuth login. On Windows PowerShell, if codex.ps1 is blocked by the execution policy, run it as cmd /c codex mcp ... When done, verify with codex mcp list. It's fine if /purpleprint:start doesn't appear in the / menu — just confirm that saying "start PurplePrint" lets you use the pp_start tool.

Press the login button and this screen appears — one tap with Google or GitHub:

You need to log in to continue.
We'll verify with your account just once.

Continue with Google
Continue with GitHub

Stuck? See Troubleshooting below.

Client UI

Find this spot inside your tool

Claude Code

> /mcp

MCP servers

Usage: /mcp [reconnect|enable|disable [<server>|all]]

/mcp

purpleprint

Remote HTTP · OAuth required · alwaysLoad true

filesystem

Connected · local stdio
Running

github

Disabled for this workspace
Disabled
Cursor Settings

Settings / Tools & MCPs

MCP Servers

Ppurpleprint

Remote HTTPS · https://purpleprint-mcp.purpleprintai.workers.dev/mcp
OAuth required
Add MCP Server
Remote HTTPS Command
Edit JSONSave
mcp.json
{
  "servers": {
    "purpleprint": {
      "url": "https://purpleprint-mcp.purpleprintai.workers.dev/mcp"
    }
  }
}

The MCP Server Definition 'purpleprint' wants you to authenticate to PurplePrint.

Cancel
Add Client Registration Details Dynamic Client Registration not supported · Client ID · Client Secret
Codex · config.toml 
# ~/.codex/config.toml
[mcp_servers.purpleprint]
url = "https://purpleprint-mcp.purpleprintai.workers.dev/mcp"

$ codex mcp add purpleprint --url https://purpleprint-mcp.purpleprintai.workers.dev/mcp

$ codex mcp login purpleprint

Opening browser for OAuth...

purpleprint · remote · authenticated

I'll set it up manually (without an agent)

Claude Code

  1. Register globally from the terminal — claude mcp add --transport http -s user purpleprint https://purpleprint-mcp.purpleprintai.workers.dev/mcp
  2. On recent IDE, add "alwaysLoad": true to mcpServers.purpleprint in ~/.claude.json — prevents missing slash commands.
  3. Open /mcp → Authenticate on purpleprint → browser login

Cursor · VS Code

  1. Register the server in user settings (~/.cursor/mcp.json or VS Code user settings):
{ "mcpServers": {
    "purpleprint": { "url": "https://purpleprint-mcp.purpleprintai.workers.dev/mcp" }
} }
  1. Browser OAuth pops up on connect → log in. (If commands don't show, restart the editor.)

Codex

  1. On Windows: cmd /c codex mcp add purpleprint --url https://purpleprint-mcp.purpleprintai.workers.dev/mcp → cmd /c codex mcp login purpleprint
  2. It's fine if slash (/purpleprint:*) doesn't appear — say “start PurplePrint” and it uses the pp_start tool.

Phase 0~9 flow

This is the heart of PurplePrint — a 10-step coaching flow that turns a daunting one-line idea into a build-ready design. So you never start alone and stuck, the coach leads one step at a time, one question at a time. Each step stacks on the previous one's conclusion, building the “why→who→what→how” purpose chain with no gaps in the middle.

How it goes — see for yourself

Try the tabs. The coach closes the gap first, you answer in plain words, and if you don't like it you can push back·debate — each of these is a way to use the product. It's not pressing “sounds good” like a general AI — you lead.

You never start staring at a blank screen. At every step the coach proposes options with a top pick and reasons, first.

purpleprint — design session

And then, a whole session end to end

How those usage modes actually play out — I followed a whole session, from Phase 0 to 9, on the one line “a cover-letter service.” Scroll and each step plays, and when a step finishes the artifact appears right there.

purpleprint — design session
Artifact Preview

Command reference

Below is the /purpleprint:<command> form for slash clients (Claude Code·Cursor). Tool clients (Codex) use the same features as pp_<command> — e.g. /purpleprint:status = pp_status.

Start · Progress

/purpleprint:startStart or resume — the first command you use. New? A warm onboarding; returning? The server remembers your last Phase·artifacts·next action and picks up right there.
/purpleprint:phase0-context … phase9-handoffCall any of the 10 step guides directly — context(0)·persona(1)·problem(2)·product(3)·UX(4)·wireframe(5)·check(6)·GTM(7)·dev design(8)·handoff(9). Usually start leads the flow, but use these to jump to a specific step.

Status · Ops

/purpleprint:statusShows at a glance which Phase you've reached, what artifacts you've made, and your next action.
/purpleprint:listLists the artifacts you've made so far (context doc·design doc, etc.).
/purpleprint:help-next-todoStuck? It points to exactly one next action from where you are.
/purpleprint:projectsGot several ideas? See your project list to switch or create a new one.
/purpleprint:saveSaves a checkpoint here. Pick up exactly there next time with start.
/purpleprint:how-to-useFirst time? A quick how-to for PurplePrint.
/purpleprint:manualA more detailed install·auth·troubleshooting manual. Reach for it when server-health doesn't resolve it.
/purpleprint:server-health“Connected but why isn't it working?” — self-diagnoses server reachability·source version·auth status and tells you per-tool recovery.
/purpleprint:oauthBriefs your login status·tier·remaining trial period.
/purpleprint:handoffBundles your finished design artifacts into a package to hand a developer or AI directly.

Growth

/purpleprint:my-growthAnalyzes your chat logs so far to measure how your builder capability has grown. It reads behavior signals only, not chat content (content-free).

Research & validation engines

The PurplePrint design coach draws your design out from what you answer. But things like “how do competitors actually do it?” or “does this persona really exist?” are information that isn't in your head. The research & validation engines fill that blank with real investigation, so your design stands on evidence rather than guesses.

What's fundamentally different from general AI — General AI (ChatGPT·Claude, etc.) makes you ask for everything — “research the competitors” — and skips it if you don't. PurplePrint proposes, inside the Phase 0~9 framework, at the right moment: “now would be a good time for this research” (💡). The coach flags what you're missing before you even know it's missing — that's the fundamental difference.

/purpleprint:hyper-researchDeeply researches competing products·tech·market → so you know “how others already solved this” and find a differentiator you won't just copy. (mainly Phase 2)
/purpleprint:hyper-research-marketingResearches competitors' channels·copy·content·community → so you start with evidence for which channels·messages land, instead of burning ad budget blindly. (mainly right after Phase 6)
/purpleprint:hyper-research-personaValidates with data whether your assumed persona actually exists → cuts the risk of betting on an “imaginary user,” and finds adjacent markets you missed. (mainly Phase 1)
/purpleprint:hyper-scenarioSimulates your design as the flow a real user goes through → catches missing scenarios·break points before you build, reducing rework. (mainly right after Phase 5)
/purpleprint:hyper-research-gtmResearches search demand·competitor channels·launch cases → so you start with a strategy for where and how to get your first users at launch. (mainly Phase 7)

How it's called — take the suggestion, call the command, and it runs on your tool's web capability directly (₩0 extra). Or call it yourself anytime. The “mainly Phase N” on each line is the best-fit moment, not the only one.

/purpleprint:hyper-review Coming soon · high tier

A premium engine that recursively checks your whole design across 39 axes (persona·value chain·revenue model·UX·GTM·security·team capability…) down to zero gaps → it quickly spots gaps an expert would take days to find, sparing you from wasting resources building on a wrong design. The 5 above run on your tool's web (free tier), but Hyper-Review runs on the server at expert depth. Mainly in the Phase 6 check.

Privacy — content-free

The design coach runs content-free — our server doesn't see what you're building or what you wrote. Exactly what lives where:

Local only — never to the server

Your idea·chat·design docs (context doc·design doc·UX doc, etc.) all live on your computer only. Research-engine results too — they run on your tool's web capability, so the content never passes through our server.

What goes to the server — progress meta only

Only progress signals like “which Phase you reached” or “how many times you used a command.” What the idea is, or what you answered — that content never goes. It's the minimum needed for resume·usage management.

Growth measurement (my-growth) is content-free too

Builder capability is measured from behavior signals (like which decisions you made yourself) without chat content. It doesn't look at what you said.

Trial · pricing FAQ

Do I need to know how to code?

No. Answer in plain words even without design terms. At each step it proposes 2~3 options and a top pick first, so you never start staring at a blank screen. Confused? Just say “again” or “simpler” and it fixes course right away.

I already have notes·a Notion doc.

Paste them and it pulls the core, normalizes it, and backfills the missing “why·who·what problem.” You don't rewrite from scratch — it fills the gaps on top of what you have.

Where are the artifacts saved?

They stack as `.md` files in your local project folder (context·design·UX docs, etc.). Next time you `start`, the server remembers your last point and resumes right there.

Which tool should I use it in?

Right now Claude Code is supported; Cursor·VS Code·Codex are coming soon. Detailed connection is in [Connect your tool] above, per tool.

Do the research engines cost anything?

Research·Scenario·Marketing·Persona·GTM run on your tool's web capability directly, so they add ₩0. Only Hyper-Review (39 axes), which uses a server LLM, is high tier.

Is it free?

Sign up and a 2-week free trial starts automatically, no card. After that, beta price $13/mo (list $20) — an add-on next to your existing AI subscription.

Why do I need to log in?

It's the minimum for account identity and trial/subscription management. Log in once with Google or GitHub and it lasts 30 days, so you don't repeat it.

Do my ideas·code go to the server?

No. Your chat·artifacts stay on your machine only. The server gets just progress meta like “which Phase you reached” (content-free). More in [Privacy] above.

I don't see slash (/) in Codex.

That's normal. Codex is a tool surface — just say “start PurplePrint” and it uses the `pp_start` tool. Stuck? Diagnose with `pp_server_health`.

Troubleshooting

Slash commands (/purpleprint:*) don't show

Connected (✓ Connected) but commands don't appear? In order:

  1. Claude Code — Open ~/.claude.json and check "alwaysLoad": true exists inside mcpServers.purpleprint. Add the line if missing. (Recent IDE may not surface slash in a fresh window without it.)
  2. Reload — Refresh the window, or type /mcp → Reconnect on purpleprint. The command list reloads.
  3. Still nothing — Fully restart the editor and open a new chat.

Disconnect is usually unnecessary — the server always keeps the list open, so reload/Reconnect is enough.

“Connected” but commands don't work (“auth required” / 401)

Commands show but execution is blocked = token expired or not attached (the server is fine). Just log in again in your tool:

  • Claude Code — /mcp → purpleprint → Authenticate (or Reconnect) → browser login
  • Cursor — Settings → Tools & MCP → purpleprint → Authenticate. If it looks connected, hit Logout once, then log back in.
  • VS Code — In MCP Servers, purpleprint → Login with PurplePrint
  • Codex — Open a new thread or restart, then “start PurplePrint”

One login lasts 30 days. No need to repeat it.

Just logged in, but the first run says “Auth required”

You logged in, but an already-open session hasn't picked up the new auth yet (especially Codex). Open a new thread or restart the editor, then run again.

There's no slash (/) at all in Codex

That's normal. Codex is a tool surface — instead of slash, say “start PurplePrint” and it uses pp_start. Stuck? Diagnose with pp_server_health.

Still stuck? — server-health (self-diagnosis: server reachability·source version·auth status + per-tool recovery) and manual (detailed install·auth·troubleshooting) tell you the recovery path directly.