kaizen-lab

KaizenLab is an AI-native hypothesis validation platform for product teams running lean startup cycles.

CommunityOnlineAPI key requiredGlobalFreeCan modify data

What it can do

  • List Projects: プロジェクト一覧を取得
  • List Canvases: プロジェクト内の仮説キャンバス一覧を取得
  • Get Canvas: 仮説キャンバスを取得（詳細）

What data it sees

Do you need an account

An API key from the service settings is required

KaizenLab is an AI-native hypothesis validation platform for product teams running lean startup cycles.

Connect your AI agent (Claude, Cursor, etc.) to access 56 MCP tools covering the full PMF validation workflow:

Core workflows:

  • 🧪 Hypothesis Canvas — create, update, and iterate on product hypotheses with sticky notes per field
  • ✅ Verification Canvas — plan experiments, run them, validate or invalidate results
  • 💡 Learnings — add, search, and analyze patterns across all learnings with AI
  • 👥 Personas & Interviews — customer research and discovery
  • 🗺️ Roadmap — prioritize next actions from validated learnings
  • 📊 PMF Score — track product-market fit progress across 5 categories

Expert mode: Use the MCP directly from Claude Code, Cursor, or any MCP-compatible client to run hypothesis validation loops entirely through your AI agent — no UI required.

Generate your API key at https://kaizen-lab.buildgeeks.dev/settings

How to connect

How to connect kaizen-lab to Claude

The server address to paste into Claude settings:

https://kaizen-lab.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect kaizen-lab to ChatGPT

The server address to paste into ChatGPT settings:

https://kaizen-lab.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect kaizen-lab to Cursor

The server address to paste into Cursor settings:

https://kaizen-lab.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (56)

Raw names from tools/list. Only developers need these.

list_projectsプロジェクト一覧を取得
list_canvasesプロジェクト内の仮説キャンバス一覧を取得
get_canvas仮説キャンバスを取得（詳細）
update_canvas仮説キャンバスを更新（名前・フェーズ）
delete_canvas仮説キャンバスを削除（関連付箋も削除）
get_pmf_scorePMFスコアを取得
add_learning学習を追加
list_learnings学習一覧を取得（ページネーション対応）
search_learnings学習を検索（queryで全文検索、tagで単一タグ絞り込み、tagsで複数タグ絞り込み）
get_verification_status検証ステータスを取得
list_personasペルソナ一覧を取得
get_interview_recordsインタビュー記録を取得
create_projectプロジェクトを作成
create_canvas仮説キャンバスを作成（fieldsの各値はstringまたはstring[]で複数付箋対応）
create_personaペルソナを作成
create_interviewインタビュー記録を作成
delete_projectプロジェクトを削除
export_projectプロジェクトをエクスポート
list_roadmapロードマップのフェーズとアイテム一覧を取得
create_roadmap_phaseロードマップフェーズを作成
create_roadmap_itemロードマップアイテムを作成
update_roadmap_itemロードマップアイテムを更新
list_verification_canvases検証キャンバス一覧を取得
get_verification_canvas検証キャンバスの詳細を取得
create_verification_canvas検証キャンバスを作成
update_verification_canvas検証キャンバスを更新
delete_verification_canvas検証キャンバスを削除
list_journey_mapsジャーニーマップ一覧を取得
create_journey_mapジャーニーマップを作成
get_learning学習の詳細を取得
update_learning学習を更新
delete_learning学習を削除
get_dashboardプロジェクトのダッシュボード（統計情報）を取得
get_changelogプロジェクトの変更履歴を取得
list_decisions意思決定ログ一覧を取得
get_decision意思決定ログの詳細を取得
create_decision意思決定ログを作成
update_decision意思決定ログを更新
delete_decision意思決定ログを削除
list_membersプロジェクトメンバー一覧を取得
invite_memberメンバーを招待（user_idとroleを指定）
update_member_roleメンバーの権限を更新
remove_memberメンバーを削除（オーナーまたは自分）
get_commentコメントの詳細を取得（全文表示）
list_commentsプロジェクトのコメント一覧を取得
create_commentコメントを作成
update_commentコメントを更新（自分のコメントのみ）
delete_commentコメントを削除（自分のコメントまたはオーナー）
list_invitations自分宛の保留中の招待一覧を取得
accept_invitation招待を承諾
reject_invitation招待を拒否
analyze_learnings蓄積された学びからパターン・矛盾・次のアクションをAI分析。analyze_all=trueで全件分析可能
analyze_competitors仮説キャンバスを元にAI競合分析を実行し結果をDBに保存（project_idはcanvas_idから自動解決可能）
add_sticky_note仮説キャンバスの付箋を追加
update_sticky_note付箋の内容を更新
delete_sticky_note付箋を削除