Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者による説明(英語の原文)
Undo a coding agent turn, including shell commands and untracked files.
この3つを1つのスコアにまとめることはしません。意見、測定、人気はそれぞれ別のものだからです。
このサーバーのやさしい解説はまだ書いていません。以下はレジストリから読み取った事実です。
使っているAIアプリを選んで、設定をコピーしてください。
必要なもの
どのアプリを使っていますか?
上でアプリを選んでください。選んだアプリを覚えておくので、次からはボタンに「…にインストール」と表示されます。
Claude Desktop → Settings → Developer → Edit Config を開き、claude_desktop_config.json にこれを貼り付けます
{
"mcpServers": {
"turnback": {
"command": "npx",
"args": [
"-y",
"turnback",
"mcp"
]
}
}
}ターミナルでこれを実行します
claude mcp add turnback -- npx -y turnback mcpプロジェクトの .cursor/mcp.json、または ~/.cursor/mcp.json に貼り付けます
{
"mcpServers": {
"turnback": {
"command": "npx",
"args": [
"-y",
"turnback",
"mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
プロジェクトの .vscode/mcp.json に貼り付けます
{
"servers": {
"turnback": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"turnback",
"mcp"
]
}
}
}ブラウザがアプリを開いてよいか確認し、そのあとアプリが設定を表示して確認を求めます。キーの値は空欄のままなので、自分で入力してください。
これはパソコンで動くサーバーですが、ChatGPTがつなげるのはインターネット上のサーバーだけです。ほかのアプリを選んでください。
選んだアプリは、この端末のCookieに保存されます。アカウントは不要です。
この設定は、作者のレジストリ登録情報から作成しています。READMEと違う場合は、READMEに従ってください。
パソコンで動くサーバーです。インストールすると、ツール一覧がAIアプリに表示されます。
誰でも見られる情報をチェックしており、コードは読んでいません。当てはまらない項目は数に入れていません。 · 2026年11月7日にチェック
レジストリ名は、リポジトリを所有するGitHubアカウント MFaizR77 で確認済みです
このリポジトリはまだGitHubから読み取っていません
このリポジトリはまだGitHubから読み取っていません
これはパソコンで動くため、インターネット上のエンドポイントはありません
パソコンで動き、代わりにローカルの設定を使います
パソコンで動くサーバーです。ツール一覧を読み取れるのは、インターネット上のエンドポイントがある場合だけです
レジストリでこのカテゴリにある有効なすべてのサーバーと比較しています。スターは、公開者がリポジトリの所有者である場合だけ数えます。
当てはまる基本チェック1項目のうち1項目に合格しました。コードは読んでいません。キーやトークンを追加する前に、サーバーがどんなアクセスを求めているかを確認し、必要な権限だけを持つキーを使ってください。
レジストリには必須のキーは載っていません。ただし、最初に使うときにサインインを求めるサーバーもあります。
あなたのパソコンで動きます。必要なときにAIアプリが起動し、データは作者のサーバーを通りません(サーバー自体がオンラインサービスを呼び出す場合を除きます)。
GitHubリポジトリの最終更新は–、最新バージョン(0.9.1)がレジストリに届いたのは23 日前です。
Claude Desktop、Claude Code、Cursor、VS CodeなどのMCP対応アプリで使えます。パソコンにNode.jsも必要です。
同じカテゴリには:Spec Driven Development, Remote Desktop Commander, Python MCP
同じカテゴリで、ほかの作者が作ったサーバー。スターの多い順。
カードの見方:★ GitHubスターi3つの柱:レビュー · チェック · 利用状況i更新=最新バージョンをレジストリに公開した日i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Local-only Python MCP server for the Files.com API.
作者のリポジトリから書かれたとおりにコピーしたものです。PopNx MCPは内容を確認・推奨していません。HTML、画像、スクリプトは取り除いています。リンクはこのサイトの外へ移動します。
Undo for AI coding agents, even after `rm -rf`.
One undo history for Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and Antigravity CLI.
A real Turnback run. The agent is simulated with Claude Code's hook payloads; the rm -rf and every Turnback line are real. Recreate it with python scripts/demo/make_demo.py.
Agent checkpoints track the agent's own edit tools. Claude Code's documentation says it plainly: "Checkpointing does not track files modified by Bash commands." So when an agent runs rm -rf, mv, a code generator, or git checkout -- ., rewind cannot bring those files back.
Turnback snapshots the workspace before every shell command and edit, into a shadow git repo under ~/.turnback:
.env) up to 5 MB are covered..git unless you run turnback export --commit, and hooks never block the agent.In Claude Code:
claude plugin marketplace add MFaizR77/turnback
claude plugin install turnback@turnback
Then use /turnback:turns, /turnback:diff-turn, /turnback:undo, and /turnback:report.
In Codex (available in the next npm release):
codex plugin marketplace add MFaizR77/turnback
codex plugin add turnback@turnback
Start a new session, review and trust Turnback's hooks in /hooks, then use $turnback:turns, $turnback:diff-turn, $turnback:undo, and $turnback:report.
The plugin needs Turnback 0.9.1 or later. To try unreleased plugin changes from a checkout, see local testing.
For Codex, Cursor, Gemini CLI, OpenCode, Antigravity CLI, or the CLI on its own (Node.js 22+ and Git 2.25+):
npm install -g turnback
turnback install all # user-level hooks and MCP for every agent turnback install codex --project # or one agent, in this project only
Claude Code, Codex, OpenCode, and Antigravity CLI have been tested live; Gemini CLI and Cursor are covered by tests built from their documented hook payloads. Details per agent: installation.
/rewind/rewind | Turnback | |
|---|---|---|
| Edits made by the agent's edit tools | ✅ | ✅ |
Files changed by shell commands (rm, mv, codegen) | ❌ | ✅ |
| Untracked and gitignored files | only files its edit tools changed | ✅ up to 5 MB |
| Other agents | ❌ | Codex, Cursor, Gemini CLI, OpenCode, Antigravity CLI |
| Go back to a point inside a turn | ❌ | ✅ --before-step |
| Rewind the conversation | ✅ | ❌ files only |
They work side by side: rewind the conversation with /rewind, and the files with Turnback.
turnback --help # commands, options, and quick-start examples
turnback list # recent turns with their prompts turnback diff # what a turn changed turnback undo --dry-run # show the plan turnback undo --yes # undo the latest turn turnback redo --yes # changed your mind turnback steps # each edit and shell command in a turn turnback restore --before-step 3 --yes turnback mark "before migration" # a checkpoint of your own turnback run -- npm run codegen # any command as an undoable turn, no agent needed turnback recover src/app.ts # bring back one file (or a folder) an agent deleted turns ago turnback blame src/auth.ts # which turn and prompt wrote each line turnback report --pr --apply # add which prompts wrote this branch to its pull request turnback du # Turnback's disk use for every workspace turnback ui # timeline in the browser
turnback run records any command as a turn, so a code generator, a codemod, or an agent without hooks gets the same undo. blame shows which turn wrote each line, and recover brings back a single file:
All commands, including log, search, report, compare, and export: commands. More: restore, MCP, scope and limits.
The hook before a mutating tool takes the turn baseline. The hook before a shell command captures the whole tree; later edits capture the affected paths. The end of the turn captures the result. The initial snapshot is warmed in the background on install and session start. Hooks always let the agent continue when recording fails; a failed, skipped, or unprotected state is visible through status.
Tracked, untracked, and gitignored files up to 5 MB are covered. Build output and dependency directories are excluded. Extra rules use gitignore syntax in .turnbackignore; global rules go in ~/.turnback/config.json as {"exclude":["pattern"]}.
Workspaces above 100k files or 2 GB switch to edits-only mode: only paths touched by edit tools are snapshotted, shell commands are recorded as unprotected, and restore touches only recorded paths. Turns older than 7 days and outside the last 50 turns are cleaned up automatically, at most once a day, in every workspace and not only the one in use. Data of a workspace that was deleted is removed after 30 idle days; set {"autoClean": false} in ~/.turnback/config.json to keep it.
Issues labeled good first issue are small and say which files they touch, and support for more agents is welcome. Start with CONTRIBUTING.md and the architecture overview. Questions and ideas go to Discussions.
Every merged pull request is credited in the release notes.
| Module | Contents |
|---|---|
src/cli/ | main.ts: CLI and hook entry point (built as dist/cli.js); args.ts: argument parsing |
src/core/ | recorder.ts: snapshot rules per event; store.ts: journal, snapshots, turns, steps, marks, status, gc; restore.ts: restore planning and execution, undo, redo; format.ts: text output; quote.ts: shell-safe arguments; journal.ts, lock.ts, config.ts, types.ts |
src/git/ | shadow.ts: shadow git repo wrapper |
src/workspace/ | workspace.ts: workspace scanning and exclusion rules |
src/agents/ | adapters.ts: each agent's hook payload → HookEvent; install.ts: hook and MCP installation per agent; opencode-plugin.ts: generated OpenCode plugin |
src/mcp/ | server.ts: stdio MCP server |
src/ui/ | server.ts: read-only local server for turnback ui; page.ts: its single page |
npm run check
npm run bench
The benchmark creates a temporary 10k-file repo and reports latency without making it a strict CI gate. CI runs the tests and benchmark on Windows, macOS, and Linux × Node 22/24.
From a clone, run npm ci && npm run build and use node dist/cli.js in place of turnback.
Set the same version in package.json and in both version fields of server.json, commit, then push a v tag. The Publish workflow checks that the versions match, runs the tests, publishes to npm through trusted publishing (provenance is attached automatically), and publishes server.json to the MCP registry as io.github.MFaizR77/turnback.
Also update src/core/config.ts, both plugin manifests, and the npm ranges in .claude-plugin/marketplace.json and .agents/plugins/marketplace.json.
npm trusted publishing is configured on the package page at npmjs.com (repository MFaizR77/turnback, workflow publish.yml), which needs the package to exist. The first version is therefore published once by hand with npm publish --access public; pushing its tag afterwards skips npm (the version exists) and only publishes to the MCP registry. Later tags do both.
MIT