Guardian MCP

Name: Guardian MCP
Author: Odingard

作者：Odingard版本 0.3.2i★ –i在你的电脑上运行

注册名称io.github.Odingard/guardian-mcp

安装

概览

作者提供的说明（英文原文）

Routes agent tool calls through Guardian for ALLOW/ASK/DENY before execution.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i尚未统计★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: stdio
分类: 其他
你需要填写：GUARDIAN_BASE_URL, GUARDIAN_AGENT_CREDENTIAL, GUARDIAN_CONNECTION_ID

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： GUARDIAN_BASE_URL, GUARDIAN_AGENT_CREDENTIAL, GUARDIAN_CONNECTION_ID, GUARDIAN_ADAPTER_ID

标为机密的值是你账户的钥匙。千万不要分享给别人，也不要粘贴到聊天里。

你需要

npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "guardian": {
      "command": "npx",
      "args": [
        "-y",
        "@odingard/guardian-mcp"
      ],
      "env": {
        "GUARDIAN_BASE_URL": "your-value",
        "GUARDIAN_AGENT_CREDENTIAL": "your-value",
        "GUARDIAN_CONNECTION_ID": "your-value",
        "GUARDIAN_ADAPTER_ID": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add guardian --env GUARDIAN_BASE_URL=your-value --env GUARDIAN_AGENT_CREDENTIAL=your-value --env GUARDIAN_CONNECTION_ID=your-value --env GUARDIAN_ADAPTER_ID=your-value -- npx -y @odingard/guardian-mcp

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "guardian": {
      "command": "npx",
      "args": [
        "-y",
        "@odingard/guardian-mcp"
      ],
      "env": {
        "GUARDIAN_BASE_URL": "your-value",
        "GUARDIAN_AGENT_CREDENTIAL": "your-value",
        "GUARDIAN_CONNECTION_ID": "your-value",
        "GUARDIAN_ADAPTER_ID": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "guardian": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@odingard/guardian-mcp"
      ],
      "env": {
        "GUARDIAN_BASE_URL": "your-value",
        "GUARDIAN_AGENT_CREDENTIAL": "your-value",
        "GUARDIAN_CONNECTION_ID": "your-value",
        "GUARDIAN_ADAPTER_ID": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

GUARDIAN_BASE_URL 必填 env
Guardian control-plane base URL
GUARDIAN_AGENT_CREDENTIAL 机密必填 env
Agent credential (gak_…)
GUARDIAN_CONNECTION_ID 必填 env
Default tool connection id for invocations
GUARDIAN_ADAPTER_ID env
Optional adapter override

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。

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6日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 Odingard 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 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

与“其他”中的其他服务器比较i

星标数多于此分类中其他 32509 个服务器的 0%
发布到注册中心的时间比此分类中其他 32509 个服务器的 95% 更新
基础检查结果等于或优于此分类中其他 32509 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

Guardian MCP 安全吗？

它在 1 项适用的基础检查中通过了 1 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？

你需要填写：GUARDIAN_BASE_URL, GUARDIAN_AGENT_CREDENTIAL, GUARDIAN_CONNECTION_ID

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–，最新版本（0.3.2）于昨天进入注册中心。

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：Spec Driven Development, Remote Desktop Commander, Fomu MCP

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ 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

Spec Driven Development

作者：formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新

安装

Remote Desktop Commander

作者：desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新

安装

Fomu MCP

作者：gabrielmahia

Kenya government form guides: checklists, draft letters, eCitizen, Huduma, timelines. Sample data.

在你的电脑上运行今天更新

安装

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。

@odingard/guardian-mcp

MCP server that routes an agent's tool calls through Guardian — Human Authority Infrastructure for Autonomous AI. Every tool call gets a deterministic ALLOW / ASK / DENY decision before anything executes; DENY means the action never runs, and ASK holds it until a human approves.

Install

npm i -g @odingard/guardian-mcp

Configure your MCP client

"mcpServers": { "guardian": { "command": "guardian-mcp", "env": { "GUARDIAN_BASE_URL": "https://guardian-api.odingard.com", "GUARDIAN_AGENT_CREDENTIAL": "gak_…", "GUARDIAN_CONNECTION_ID": "con_…" } } } }

GUARDIAN_ADAPTER_ID optionally overrides the tool adapter.

Tools

Tool	What it does
`guardian_invoke_tool`	Propose a tool call. ALLOW executes and returns the receipt; ASK returns a `requestId` held for human approval; DENY refuses with a reason code.
`guardian_claim`	Claim an approved ASK by `requestId`, execute, return the receipt.
`guardian_receipt`	Fetch the machine-readable evidence receipts for a request.

Nothing executes without a Guardian capability — the model's output is a proposal, never an action.

Govern an existing MCP server: `guardian-mcp proxy` (0.3)

Put Guardian in front of any stdio MCP server you already use, such as WhatsApp, Stripe, Shopify, a filesystem or a database. The client sees the upstream server's tools unchanged, and every call is decided first:

"mcpServers": { "whatsapp-governed": { "command": "guardian-mcp", "args": ["proxy", "--", "npx", "-y", "your-whatsapp-mcp-server"], "env": { "GUARDIAN_BASE_URL": "https://guardian-api.odingard.com", "GUARDIAN_AGENT_CREDENTIAL": "gac1.…", "GUARDIAN_CONNECTION_ID": "con_…", "WHATSAPP_TOKEN": "…" } } } }

Decision	What happens
ALLOW	The call is forwarded to the upstream server, then the capability is redeemed and the receipt recorded.
ASK	Nothing is forwarded. The exact call is held under a `requestId`; after a human approves, `guardian_claim` forwards exactly that call, once.
DENY	Nothing is forwarded, ever. The same applies if Guardian is unreachable.

guardian_claim and guardian_receipt are added to the tool list.
The upstream server never receives GUARDIAN_* settings, so it never sees the agent credential.
Decision-gated: an allowed call runs upstream before the capability is redeemed. A refusal at redemption is reported as an incident (localEffectRan: true), never as success.
First-run setup: in the Guardian console, connect a tool server and add each upstream tool as "My own code (record-only)". Then allow those tools for the agent.
Since 0.3.1 the proxy does not try to register tools itself.
GUARDIAN_AUTO_REGISTER=true turns that back on, but it is denied unless the agent's grant pins mcp.install.
When Guardian refuses, the result says what to fix.
Held calls live in the proxy process. Restarting the proxy drops them, and nothing is forwarded.

guardian-mcp --help prints usage. A missing setting prints a one-line message naming it instead of a stack trace.

See what you are about to govern: `guardian-mcp tools`

Before putting a server behind the proxy, list its tools along with a suggested Guardian mode for each. This needs no Guardian credential:

npx -y @odingard/guardian-mcp tools -- npx -y @modelcontextprotocol/server-filesystem ./data

Tool            Suggested     Why

read_file Allow server marks it read-only write_file Ask me first "write" may change something delete_branch Ask me first server marks it destructive createIssue Ask me first "create" may change something ⚠ name not accepted by Guardian

How the suggestions are made:

The server's own MCP annotations (readOnlyHint, destructiveHint) are used first.
Otherwise the tool's verb decides. get, list and search suggest Allow; everything else suggests Ask.

They are suggestions only: you set the real modes in the console. Tool names that break Guardian's naming rule are flagged, because every call to them would be denied. Add --json for machine-readable output.

License

Apache-2.0. Canonical development happens in the Odingard Guardian monorepo.