VibeRevert
What it does
Local MCP server for AI coding safety: risk checks, sessions, checkpoints, and fix prompts.
- Connects 在你的电脑上运行
- Account or key No key needed
- Category 搜索与 AI 记忆
安装
选择你使用的 AI 应用,然后复制设置。
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月13日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Node.js(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
打开电脑版 Claude 应用的设置文件
SettingsDeveloperEdit Config
粘贴这些设置并保存文件
{ "mcpServers": { "viberevert": { "command": "npx", "args": [ "-y", "viberevert", "mcp", "serve" ] } } }退出 Claude 再重新打开
试一试
用 VibeRevert 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 VibeRevert,或回答中出现 VibeRevert 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 VibeRevert
VibeRevert 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
你可以改用这些方式
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --scope user viberevert -- npx -y viberevert mcp serve在 Claude Code 中输入 /mcp
应能看到 VibeRevert 在列表中并显示已连接
试一试
用 VibeRevert 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 VibeRevert,或回答中出现 VibeRevert 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 VibeRevert 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 VibeRevert,或回答中出现 VibeRevert 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Node.js(只需一次)
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 VibeRevert 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 VibeRevert,或回答中出现 VibeRevert 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
开发者专用:终端命令和 JSON 设置
安装在电脑上
Claude Code
claude mcp add --scope user viberevert -- npx -y viberevert mcp serveClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"viberevert": {
"command": "npx",
"args": [
"-y",
"viberevert",
"mcp",
"serve"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"viberevert": {
"command": "npx",
"args": [
"-y",
"viberevert",
"mcp",
"serve"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"viberevert": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"viberevert",
"mcp",
"serve"
]
}
}
}这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
基础检查i
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月14日
- ✓ 通过
作者与仓库一致
注册名称已通过域名 viberevert.com 验证(注册中心会核实域名所有权)
- ✓ 通过
仍在维护
代码最后更新于2个月前
- ✓ 通过
有许可证
使用 Apache-2.0
- – 不适用
端点有响应
它在你的电脑上运行,没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行,改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行;我们只能读取互联网端点的工具列表
讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“搜索与 AI 记忆”中的其他服务器比较i
- 星标数多于此分类中其他 6075 个服务器的 0%
- 发布到注册中心的时间比此分类中其他 6075 个服务器的 29% 更新
- 基础检查结果等于或优于此分类中其他 6075 个服务器的 100%
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
常见问题
VibeRevert 安全吗?
它在 3 项适用的基础检查中通过了 3 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在我的电脑上运行还是在云端?
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
它还在维护吗?
GitHub 仓库最后更新于2个月前,最新版本(0.7.1-beta.4)于3个月前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
有什么可以替代它?
同一分类中有:Context7, Codebase Memory, OpenSEO
同类别的其他选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Codebase Memory
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
OpenSEO
Keyword research, site audits, rank tracking and AI visibility for your AI agent.
作者的 README
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
VibeRevert
Protect the project you're actually working on.
Record · Check · Fix · Restore.
VibeRevert is the project-integrity layer for AI coding. It records the real working state before an agent starts, flags risky changes with deterministic rules, and lets you remove the agent work you don't want without giving up the rest.
An agent changed 80 files. 75 are useful. Remove the 5 you don't.
No AI judges the AI: risk findings are reproducible, explainable, and based on rules you can inspect.
The working state you already had is part of the project. Staged work, unstaged edits and pre-existing untracked files are recorded before the session starts and preserved through recovery. You don't have to package your work into commits before letting an agent help with it.
Keep using your coding agent. VibeRevert works alongside Claude Code, Cursor, and other coding-agent workflows. Git worktrees give an agent an isolated checkout; VibeRevert protects and selectively recovers the working state an agent actually changes. They solve different problems and can be used together.
*AI broke your project? Undo the session, not your week.* Whole-session rollback is still one command.
See it work
The actual CLI, condensed from a real beta payment run — check flags it, and rollback previews what it will change before you --apply:
$ viberevert check
risk: CRITICAL · payments app/api/checkout/route.ts payments (critical) app/api/webhooks/stripe/route.ts payments (critical)
$ viberevert rollback # preview — nothing changed yet package.json tracked_restored app/page.tsx tracked_restored app/api/checkout/route.ts untracked_deleted app/api/webhooks/stripe/route.ts untracked_deleted lib/stripe.ts untracked_deleted .gitignore README.md (your uncommitted work) skipped_unchanged
Proof, not promises
3 real AI coding sessions. 3 exact project-file restorations. Payments, database migrations, and deployment infrastructure — all with pre-existing uncommitted work preserved. Read the beta report →
Quickstart
Works inside a Git repository and requires Node.js 22+. VibeRevert keeps its records on your machine and requires no VibeRevert account or hosted service.
npm install -g viberevert@beta
viberevert init # one-time setup in your project
viberevert run # records the session and saves your files' starting state viberevert check # see what changed and what looks risky viberevert rollback # preview putting your files back; add --apply to restore
Restoring only part of a session works the same way, with a selector:
viberevert rollback <session> --only 'app/api/**' # preview just that part
viberevert rollback --only 'app/api/**' --apply # restore just that part
What it protects you from
You let an AI agent work across your project, and it touched more than you expected — maybe payment code, a database migration, a deploy file — while your own half-finished work was sitting right there uncommitted. VibeRevert captures your project's starting file state first, so a session you don't like doesn't cost you your afternoon.
What VibeRevert does
Around each AI coding session, VibeRevert:
- Checkpoints your project first — working tree, staged changes, and untracked files, including work you haven't committed.
- Records the session and the project files that changed while it ran.
- Flags risky edits — changes touching auth, payments, databases, secrets, dependencies, or infrastructure (risk taxonomy).
- Writes an agent-ready fix prompt from those findings, to paste into your next iteration.
- Restores your files to the checkpoint when you need it.
It warns you; it does not silently block your work. An optional pre-commit hook can reject a commit above your configured risk threshold — opt-in, tunable, and bypassable like any local Git hook.
Rules decide. Agents fix.
VibeRevert does not ask another language model whether your agent's changes look risky. Its checks are deterministic: the same inputs and configuration produce the same findings, with an inspectable reason for every flag.
When something needs attention, VibeRevert can turn those findings into an agent-ready fix prompt. The rules decide what to flag; you decide what happens next.
Roll back all of it, or only the part that went wrong
viberevert rollback restores your local project files — tracked, staged, and untracked, including uncommitted work — to how they were when the session started. It previews by default; --apply writes the change, and every apply first saves an emergency checkpoint you can recover from.
Since 0.8.0 you can also restore part of a session. Say the agent's payments change was wrong but its test additions were fine: put back only the payments work and keep everything else.
$ viberevert rollback <session> --only 'app/api/**' # preview — nothing changed yet
[RESTORED] app/api/checkout/route.ts [RESTORED] app/api/webhooks/stripe/route.ts Eligibility: eligible
$ viberevert rollback --only 'app/api/**' --apply
Four ways to choose, and any one of them switches rollback into selective mode:
| Selector | Picks |
|---|---|
--only | changes matching a path pattern |
--except | everything but those, subtracted last |
--risk | changes a finding rated at or above that level touches |
--finding | the changes one specific finding applies to |
Positive selectors combine by intersection, so --only 'payments/**' --risk critical means critical changes inside payments/, not payments plus every unrelated critical file. Path selectors follow a renamed file, so a file moved out of payments/ still matches. Nothing is restored unless everything you selected can be: if any selected path drifted since the session ended, the whole operation refuses rather than half-applying, and --force does not override that. If a selective apply is interrupted, the next one fails closed and points you at the emergency checkpoint rather than layering a second partial restore on top.
Two current limitations worth knowing before you rely on it:
- Sessions ended before 0.8.0 cannot be selectively rolled back. They have no record of what they contributed and it cannot be reconstructed. Whole-session rollback still works on them, unchanged. See MIGRATIONS.md.
- `--finding` needs the full finding id, as printed by
viberevert check --since --json. Short prefixes are not accepted yet.
It does not reverse effects outside your project files. Deployments, database writes, third-party API calls, payments, and sent emails need their own recovery. Rollback is state-based rather than atomic, and it's a safety net around AI sessions, not a replacement for tests or review. Read what rollback can and can't restore before you rely on it.
One recovery layer across your coding agents
Keep using the coding tools you prefer. VibeRevert can wrap command-line agent sessions (viberevert run ) and integrates with tools such as Claude Code and Cursor through its installers.
Built-in checkpoints live inside the agent's workflow. VibeRevert stays with the project.
It captures your project's starting state — including uncommitted work — then records the session, flags risky changes, previews the rollback, and keeps that recovery path outside the agent itself.
Use Claude Code today, Cursor tomorrow, or wrap another terminal agent: the safety layer stays with your project.
Wire it into your tools
VibeRevert installs non-destructively and can be removed cleanly. It integrates with Claude Code and Cursor (MCP server and hooks); every install previews its changes and keeps a recovery journal. See getting started.
An experimental terminal bridge (--pty) can intercept commands inside an interactive agent shell; it's best-effort and documented as such in the PTY contract.
Platforms
Linux, macOS, and Windows, on Node.js 22+. CI runs the suite across all three on Node 22 and 24; see compatibility for exactly what each platform is tested to do.
Learn more
- Getting started · Commands · Configuration
- What rollback can and can't restore · Risk taxonomy
- Security policy · Threat model · Contributing
Support VibeRevert
VibeRevert is Apache-2.0 open source. Sponsoring funds continued cross-platform testing, security work, rollback and recovery testing, and helping pay for independent review. Sponsorship does not influence risk findings or release decisions. → [Sponsor VibeRevert](https://github.com/sponsors/madeinplutofabio?metadata_campaign=viberevert) · what your support funds
License
Apache-2.0. See NOTICE and the license audit.