AI Skill Hub 推荐使用:ThumbGate MCP工具 是一款优质的MCP工具。AI 综合评分 7.2 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
ThumbGate MCP工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
ThumbGate MCP工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/IgorGanapolsky/ThumbGate
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"thumbgate-mcp--": {
"command": "npx",
"args": ["-y", "thumbgate"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 ThumbGate MCP工具 执行以下任务... Claude: [自动调用 ThumbGate MCP工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"thumbgate_mcp__": {
"command": "npx",
"args": ["-y", "thumbgate"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <a href="https://thumbgate.ai"> <img src="docs/media/thumbgate-hero-banner.svg" alt="ThumbGate Infrastructure Firewall with Thumbs Up and Thumbs Down" width="100%" /> </a> </p>
<p align="center"> <b>ThumbGate is the self-improving pre-action firewall for AI coding agents</b><br> AI coding agents repeat mistakes — and one wrong tool call can wipe a directory, leak a key, or push broken code. </p>
<p align="center"> <a href="https://mcptoplist.com/server/glama%2FIgorGanapolsky%2FThumbGate"><img src="https://mcptoplist.com/badge/glama%2FIgorGanapolsky%2FThumbGate.svg" alt="MCP Toplist" /></a> <a href="https://github.com/IgorGanapolsky/ThumbGate/actions/workflows/ci.yml"><img src="https://github.com/IgorGanapolsky/ThumbGate/actions/workflows/ci.yml/badge.svg" alt="CI" /></a> <a href="https://www.npmjs.com/package/thumbgate"><img src="https://img.shields.io/npm/v/thumbgate" alt="npm version" /></a> <a href="https://www.npmjs.com/package/thumbgate"><img src="https://img.shields.io/npm/dw/thumbgate" alt="npm weekly downloads" /></a> <a href="https://github.com/IgorGanapolsky/ThumbGate"><img src="https://img.shields.io/github/stars/IgorGanapolsky/ThumbGate" alt="GitHub stars" /></a> <a href="https://github.com/marketplace/actions/thumbgate-agent-governance"><img src="https://img.shields.io/badge/GitHub_Marketplace-ThumbGate_Agent_Governance-0969da" alt="GitHub Marketplace: ThumbGate Agent Governance" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-green.svg" alt="License: MIT" /></a> </p>
<p align="center"> <a href="#quick-start"><img src="https://img.shields.io/badge/⚡_Quick_Start-npx_thumbgate_init-22d3ee?style=for-the-badge" alt="Quick Start" /></a> <a href="https://thumbgate.ai/#demo?utm_source=github&utm_medium=readme"><img src="https://img.shields.io/badge/🎬_Watch-90s_Demo-ff647c?style=for-the-badge" alt="Watch Demo" /></a> <a href="https://thumbgate.ai/go/gpt?utm_source=github&utm_medium=readme"><img src="https://img.shields.io/badge/💬_Try-ThumbGate_GPT-56e39f?style=for-the-badge" alt="Try GPT" /></a> <a href="https://thumbgate.ai/checkout/pro?utm_source=github&utm_medium=readme"><img src="https://img.shields.io/badge/💼_Pro-$19/mo-ffd166?style=for-the-badge" alt="Pro Tier" /></a> </p>
---
Directories and clients that install ThumbGate as an MCP server must start stdio MCP, not the HTTP API:
npx -y thumbgate serve
npx -y thumbgate mcpnpm start for MCP — that launches the hosted HTTP API (src/api/server.js), not the agent-facing stdio server.▶ 90-second demo · GIF walkthrough
---
| Agent | Command | Enforcement |
|---|---|---|
| **Claude Code** | npx thumbgate init --agent claude-code | 🛡️ Hard — PreToolUse |
| **Codex** | npx thumbgate init --agent codex | 🛡️ Hard — pre_tool_use |
| **Gemini CLI** | npx thumbgate init --agent gemini | 🛡️ Hard — PreToolUse |
| **ForgeCode** | npx thumbgate init --agent forge | 🛡️ Hard — pre_tool_use |
| **Cursor** | npx thumbgate init --agent cursor | 💬 Advisory — MCP gate_check |
| **Cline** | npx thumbgate init --agent cline | 💬 Advisory — MCP + .clinerules |
| **OpenCode** | npx thumbgate init --agent opencode | 💬 Advisory — MCP gate_check |
| **Any MCP agent** | npx thumbgate serve | 💬 Advisory — MCP gate_check |
| **Amp** | npx thumbgate init --agent amp | 📝 Feedback capture |
| **GitHub Actions** | uses: IgorGanapolsky/ThumbGate@v1 | 🩺 Marketplace Action — doctor / AI inventory in CI |
Per-agent guides: Claude/Codex bridge · Codex profile · Cursor · MCP setup
Igor Ganapolsky — payments (Stripe/Connect), AI agent guardrails/MCP, Android + backends. Small number of contract slots: $120–150/hr, 1099, remote US. LinkedIn · thumbgate.ai
Want a phased walkthrough with a verify step at every stage? Follow the Progressive Setup Guide.
Progressive wiring — prove the pipe before you turn matching on. Empty dashboard is success.
npx thumbgate init # Phase 1: hooks only
npx thumbgate doctor # verify: exits 0 only when PreToolUse hook is wired (hidden metric = hook install, not gate count)
npx thumbgate dashboard --open # Phase 2: open local HTML; empty stats are OK
npx thumbgate capture --feedback=down --context="Never run DROP on production tables" --what-went-wrong="agent proposed DROP" --what-to-change="require review for DROP"
Later DROP attempts in the same scope surface the check:
⚠️ Check fired: "Never run DROP on production tables"
Pattern: DROP.*production
Verdict: 👎 WARN + LOG (⛔ BLOCK when THUMBGATE_STRICT_ENFORCEMENT=1)
Numbered configs: config/progressive/. Guide: progressive wiring.
| Surface | Start here |
|---|---|
| **Open ThumbGate GPT** | [thumbgate.ai/go/gpt](https://thumbgate.ai/go/gpt?utm_source=github&utm_medium=readme&utm_campaign=readme_gpt) — **ThumbGate GPT: start here.** Paste agent actions, get advice + checkpointing. **No, users do not have to keep chatting inside the ThumbGate GPT to use ThumbGate** — the **hard enforcement layer still runs where the work happens**. |
| **Install Codex Plugin** | Open the Codex plugin install page: [thumbgate.ai/codex-plugin](https://thumbgate.ai/codex-plugin) · zip: [thumbgate-codex-plugin.zip](https://github.com/IgorGanapolsky/ThumbGate/releases/latest/download/thumbgate-codex-plugin.zip) · [plugins/codex-profile/INSTALL.md](plugins/codex-profile/INSTALL.md) |
Claude Desktop .mcpb | [latest release](https://github.com/IgorGanapolsky/ThumbGate/releases/latest/download/thumbgate-claude-desktop.mcpb) |
| **VS Code / Open VSX** | [plugins/vscode-extension/README.md](plugins/vscode-extension/README.md) |
| **Antigravity-compatible** | [plugins/antigravity-extension/INSTALL.md](plugins/antigravity-extension/INSTALL.md) |
| **JetBrains** | [plugins/jetbrains-plugin/README.md](plugins/jetbrains-plugin/README.md) · JetBrains Marketplace path for the same runtime |
| ChatGPT App / GPT Action | [thumbgate.ai/chatgpt-app](https://thumbgate.ai/chatgpt-app) |
| ThumbGate-Core (staging) | [https://github.com/IgorGanapolsky/ThumbGate-Core](https://github.com/IgorGanapolsky/ThumbGate-Core) — pre-release staging + a few internal cache scripts; **not** the product moat |
| Scope | Command | Settings | Lessons | Best for |
|---|---|---|---|---|
| **Machine-wide** (default) | npx thumbgate init | ~/.claude/settings.json | ~/.claude/memory/feedback/ | Solo operators — **same machine-local feedback store** across repos |
| **Per-project** | npx thumbgate init --project | <repo>/.claude/settings.json | <repo>/.claude/memory/feedback/ | Client / compliance — **separate dashboard** / isolated lessons per repo |
Both scopes write mcpServers.thumbgate plus PreToolUse / UserPromptSubmit / PostToolUse / SessionStart hooks. Machine-wide is the right default for most developers. Cross-repo blocking is not automatic: a lesson learned in one project only applies elsewhere when you share the store (machine-wide) or export/import lessons.
MCP tools (surface): gate_check (read/evaluate proposed tool call), feedback capture + session tools (write), dashboard/stats (read). Destructive agent actions stay blocked/warned by PreToolUse — ThumbGate does not execute user shell commands for you.
---
ThumbGate 是一款专为 AI Agent 设计的“错误预防”工具。在当前的 AI 开发流程中,Agent 频繁出现的幻觉、重复错误的 Tool Call 或无效的指令重试,不仅消耗开发者的精力,更会带来高昂的 API 调用成本(如 Claude Sonnet/Opus 等模型)。ThumbGate 通过记录用户的负面反馈,将其转化为永久性的预防规则,确保一旦某个错误被标记,它将在所有 Session、所有 Agent 及所有模式下被自动拦截,实现“一次纠错,终身受益”。
ThumbGate 支持多种主流 AI 开发工具的快速集成。对于 Claude Code 或 Cursor 用户,可以通过运行 `npx thumbgate init --agent <agent-name>` 命令进行初始化。VS Code 用户可通过插件市场安装扩展,JetBrains 用户亦有相应插件支持。此外,针对 Codex 用户,可以通过官方安装页面或 GitHub Releases 下载插件包,Codex Launcher 会自动解析最新的 `thumbgate@latest`,无需手动修改 `~/.codex/config.toml` 配置文件。
使用 ThumbGate 非常简单。首先通过 `npx thumbgate init` 自动检测并配置您的 Agent 环境。当 Agent 出现错误行为时,您只需运行 `npx thumbgate capture --feedback=down --context="错误描述"`,即可将该行为捕获为一条预防规则。下次当任何 AI Agent 尝试执行匹配该模式(Pattern)的危险操作时,ThumbGate 会直接拦截并显示拦截原因,防止错误再次发生。
ThumbGate 提供了一套完整的 CLI 工具集用于管理规则与状态。使用 `npx thumbgate init` 进行环境初始化与 Hook 绑定;使用 `npx thumbgate doctor` 进行健康检查;使用 `npx thumbgate capture` 捕获反馈并将其存储为“教训(Lesson)”;使用 `npx thumbgate lessons` 查看已学习的规则;最后通过 `npx thumbgate explore` 进入终端交互模式,对规则和检查项进行深度探索。
ThumbGate 提供了强大的集成能力。您可以利用专用的 ThumbGate GPT 作为起点,通过粘贴 Agent 的动作来获取建议并进行 Checkpointing。值得注意的是,ThumbGate GPT 仅作为辅助工具,用户无需全程在 GPT 中交互,即可在本地开发环境中享受其带来的自动化拦截与规则管理能力。
ThumbGate 并非模型微调(Fine-tuning)工具,它不改变模型权重,而是通过在运行时注入 Context 并拦截动作来发挥作用。与 `CLAUDE.md` 或 `.cursorrules` 等静态提示词文件不同,ThumbGate 提供的规则具有强制性,能够有效防止 Agent 忽略指令,确保反馈在不同会话间具备持久的记忆力。
创新的Agent治理方案,将用户反馈转化为系统控制机制。低星数但概念新颖,适合关注AI安全和成本优化的团队探索。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,ThumbGate MCP工具 是一款质量良好的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | ThumbGate |
| 原始描述 | 开源MCP工具:Agent governance for ThumbGate: 👍/👎 become Pre-Action Checks that block repeat。⭐18 · JavaScript |
| Topics | Agent治理成本优化AI安全行动检查JavaScript |
| GitHub | https://github.com/IgorGanapolsky/ThumbGate |
| License | MIT |
| 语言 | JavaScript |
收录时间:2026-05-17 · 更新时间:2026-05-23 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端