AI Guardian

Name: AI Guardian
Author: AIops-tools

作者：AIops-tools版本 0.14.0i★ –i在你的电脑上运行

注册名称io.github.AIops-tools/ai-guardian

安装

概览

作者提供的说明（英文原文）

Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.

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: 搜索与 AI 记忆

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）。
注册中心没有列出需要填写的密钥。

你需要

PyPI已安装 Python 的 uv（用于 uvx 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": {
    "ai-guardian": {
      "command": "uvx",
      "args": [
        "ai-guardian-aiops"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add ai-guardian -- uvx ai-guardian-aiops

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": {
    "ai-guardian": {
      "command": "uvx",
      "args": [
        "ai-guardian-aiops"
      ]
    }
  }
}

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": {
    "ai-guardian": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ai-guardian-aiops"
      ]
    }
  }
}

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。

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8日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 AIops-tools 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“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 5678 个服务器的 0%
发布到注册中心的时间比此分类中其他 5678 个服务器的 81% 更新
基础检查结果等于或优于此分类中其他 5678 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

AI Guardian 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？

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–，最新版本（0.14.0）于9天前进入注册中心。

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 Python (uv)。

有什么可以替代它？

同一分类中有：Context7, Codebase Memory, Exa

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

Context7

作者：upstash

Up-to-date docs for AI agents

电脑或云端★ 64,224MIT昨天更新

安装

Codebase Memory

作者：DeusData

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

在你的电脑上运行★ 48,148MIT21天前更新

安装

Exa

作者：exa-labs

Connect AI agents to Exa for web search, content fetching, and multi-step research.

在云端运行★ 5,213MIT2个月前更新

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。

AI Guardian

Audit availability: Real writes require a committed pending audit row and stop before contacting the platform if storage is unavailable. Reads and previews may continue with a warning; new audit rows store outcome summaries rather than full responses.

Disclaimer: Community-maintained open-source project. Not affiliated with, endorsed by, or sponsored by Ollama, IGEL, or any AI-security vendor. Product and trademark names belong to their owners. MIT licensed.

Governed observability + governance for on-endpoint local LLMs. It lets you observe + audit what your local models are actually fed, and gate what leaves in a prompt — the complement to IGEL AI Armor. AI Armor governs *whether* a local model may run on the endpoint; ai-guardian records *what it did* and gates *what goes into the prompt* (secrets, PII, source, jailbreaks) plus *which model* may serve it. Self-contained: it talks to each runtime's REST API and needs nothing beyond httpx and the MCP SDK. v0.1 provides opt-in route-through content governance, plus a transparent capture proxy for clients that did not opt in.

Supported runtimes

One tool, several local runtimes, selected per target by a runtime field in config.yaml (the init wizard asks). Ollama uses its native API; the other three share one OpenAI-compatible transport (/v1/models + /v1/chat/completions).

Runtime	`runtime`	Default port	List / policy	Scan + route-through guard	Provenance
Ollama	`ollama`	11434	✅	✅	digest (content hash — strong)
llama.cpp (`llama-server`)	`llamacpp`	8080	✅	✅	props — `/props` model path/size → pinnable id
LM Studio	`lmstudio`	1234	✅	✅	id only — weaker; pins report `unverifiable`
vLLM (local single-node)	`vllm`	8000	✅	✅	id only — weaker; pins report `unverifiable`

The allow/deny model policy, the deterministic prompt scanner, the route-through guard (guarded_generate / observe_chat), provenance drift, and doctor work across all runtimes. Model lifecycle writes (pull / remove / unload) are Ollama-only — the OpenAI-compatible servers load a model at startup and expose no lifecycle endpoint, so those writes are refused with a clear message.

Provenance honesty: only Ollama (content digest) and llama.cpp (a /props-derived path/size identity) expose something to pin. LM Studio and vLLM expose only a model id, so a pinned digest is reported unverifiable rather than a false DRIFT.

vLLM here is a LOCAL endpoint-guarding use case. GPU inference-cluster

operations (autoscale, drain, Ray Serve/Jobs, model lifecycle at fleet scale)

belong to a different tool in the line — GPU cluster ops → inference-aiops.

What it does

Ollama persists no queryable prompt/response history — conversational context is client-supplied on every request. So ai-guardian observes on two fronts:

Passive inventory / state auditing — over /api/tags, /api/ps, /api/show, /api/version: what models are installed and running, their VRAM residency, license/params/capabilities, and their provenance digests. Every model is annotated with an allow/deny policy verdict, so shadow (unsanctioned) models show allowed: false.
Opt-in route-through content governance — callers send a prompt *through* ai-guardian (guarded_generate / observe_chat). It scans the text (secrets / PII / source / jailbreak), checks the model against policy, records the interaction to its own usage log (~/.ai-guardian/usage.db), and only then calls Ollama — blocking when the risk band is too high or the model is disallowed. The raw prompt is never stored (only its length + redacted findings).

Now available (ai-guardian proxy serve): a transparent capture proxy that

applies the same scan + model policy + recording to traffic from clients that

never opted in — point them at the proxy instead of the runtime. It inspects

requests and streams responses through untouched, and it is a

chokepoint, not an enforcement boundary: a client that can still reach the

runtime's real port bypasses it entirely. proxy_guidance returns the command

and that caveat; the CLI prints it on every start.

Key features

Deterministic, offline prompt scanner — no I/O, no network, so it is fully testable offline. Flags secrets (AWS AKIA, private-key blocks, GitHub / Slack / OpenAI / Google tokens, JWTs, assigned api_key=…, high-entropy fallback), PII (email, US SSN, credit card with a Luhn check), source/config-leak heuristics, and jailbreak / prompt-injection signatures — rolled up into a weighted risk band (low / medium / high / critical; any critical dominates). Findings are redacted — the scanner never re-emits the secret it caught.
Model allow/deny policy (shell-glob patterns) so shadow / unsanctioned models surface as allowed: false, plus provenance digest pinning to flag a model whose digest drifted (re-pulled / tampered).
Route-through guard — guarded_generate / observe_chat scan + policy-gate
record + run-if-allowed, blocking on risk-band >= block_threshold (default high) or a disallowed model.
Vendored governance harness — audit log, token/runaway budget guard, descriptive risk tiers, and undo-token recording, bundled in the package (no external dependency).
Highly self-testable — Ollama is free + local for the API parts; the scanner, policy, and risk-band are pure deterministic offline logic.

What this tool does, and does not, decide

It delivers local-LLM observability and operations — reads and writes — accurately, and records every one of them. It does not decide whether a write to the model estate is allowed to happen. That is the agent's judgement, or the permission of the host and account you run it under: point it at a runtime the account cannot administer — an Ollama daemon whose model store the user can't modify, or an endpoint the agent reaches read-only — and the writes fail at the runtime, the place that actually owns the permission. Simplest of all, hand the connecting agent only the scan/observe tools.

So the harness has no read-only switch, no deny-rules file, and no approval gate to configure. (Content governance is a separate, product-level thing that stays: the model allow/deny policy and the guarded_generate block threshold still scan and gate what a model is asked to do.) The one thing the harness guarantees is that nothing is silent: every call, over MCP and over the CLI alike, lands an audit row in ~/.ai-guardian/audit.db, and destructive writes still capture their before-state and record an inverse where one exists.

Each tool declares a risk_level, kept in agreement with its [READ]/[WRITE]

documentation tag by a test, and carried into the audit row as a descriptive

tier — so a reviewer can see at a glance that a row was a high-risk delete. It

is a label, not a gate.

Running a smaller / local model? See agent-guardrails.md — it lists the guardrails this tool now enforces for you (so you don't spend prompt budget restating them) and gives a ready-made system prompt for what's left.

Capability matrix (21 MCP tools)

Reads (11)

Tool	Risk	What it returns
`list_models`	low	installed models, each with the allow/deny verdict (shadow → `allowed:false`)
`running_models`	low	loaded models: VRAM footprint + residency expiry
`model_details`	low	license / parameters / capabilities for one model
`server_status`	low	Ollama reachability + version
`vram_usage`	low	total VRAM used by loaded models; flag over-budget
`policy_view`	low	current allow/deny policy + provenance digest pins
`model_provenance`	low	each installed digest vs its pin; flag drift
`scan_prompt`	low	pure text scan → findings + weighted risk band (no model call)
`usage_events`	low	query the observed-usage log
`anomaly_report`	low	rollup: shadow models, digest drift, high-risk + blocked prompts
`proxy_guidance`	low	the `proxy serve` command + the client change, and the explicit caveat that the proxy is a chokepoint, not an enforcement boundary; writes nothing, starts nothing

Writes (8)

Tool	Risk	Undo / safety
`pull_model`	medium	refused if it violates policy
`remove_model`	high	dry-run + undo (re-pull)
`unload_model`	medium	evict from VRAM (`keep_alive:0`)
`set_model_allowlist`	medium	undo → prior allowlist
`set_model_denylist`	medium	undo → prior denylist
`pin_model_digest`	medium	pin a model's expected provenance digest
`guarded_generate`	medium	the route-through guard: scan + policy-gate + record + run-if-allowed
`observe_chat`	medium	same, for `/api/chat` messages

Undo (2)

Tool	Risk	What it does
`undo_list`	low	list recorded undo tokens
`undo_apply`	medium	replay a recorded inverse descriptor

Risk-band gating: guarded_generate / observe_chat block when the prompt's risk band >= block_threshold (default high) or the model is disallowed. Blocked calls never reach Ollama and are recorded as blocked in the usage log.

Quick start

As a Claude Code plugin

One install gives an agent both the skill and the MCP server:

/plugin marketplace add AIops-tools/marketplace

/plugin install ai-guardian@aiops-tools

The MCP server is fetched with uv and pinned to the package version this plugin declares, so an audit row can be traced back to the code that wrote it. Credentials are still configured with ai-guardian init — see below.

As an OpenClaw plugin

The same bundle is published on ClawHub, where one install delivers the skill and its MCP server together:

openclaw plugins install clawhub:@zw008/ai-guardian

openclaw skills info ai-guardian # expect: Visible to model: yes

Restart the OpenClaw gateway afterwards so it loads the plugin. The MCP server is fetched with uv, pinned to this exact release, so uvx has to be on PATH — without it the skill still installs but reports Visible to model: no. Credentials are configured exactly as below.

As a CLI or standalone MCP server

uv tool install ai-guardian-aiops          # or: pipx install ai-guardian-aiops

ai-guardian doctor # Ollama reachability + policy summary (works zero-config) ai-guardian overview # models installed/running, shadow count, usage stats ai-guardian model list # installed models with allow/deny verdicts ai-guardian guard scan "my key is [PopNx MCP ตัดค่าที่หน้าตาเหมือนกุญแจออก]" # deterministic scan → risk band

The command and the package have different names. The CLI, the skill and

this repo are all ai-guardian; the PyPI distribution is `ai-guardian-aiops`

because ai-guardian was already taken. Both spellings below are correct and

intentional — install ai-guardian-aiops, then run ai-guardian.

Route a prompt through the guard (scan + policy-gate + record + run-if-allowed) via MCP:

guarded_generate(model="llama3.2:3b", prompt="…", block_threshold="high")

Run as an MCP server (stdio) — the full 21-tool surface; the CLI is a convenience subset:

export AI_GUARDIAN_AIOPS_MASTER_PASSWORD=...   # only if a target has a stored token

ai-guardian mcp # or: ai-guardian-mcp

**Where that pas

只显示了开头部分；其余内容请在仓库中阅读

AI Guardian

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“搜索与 AI 记忆”中的其他服务器比较i

常见问题

替代选择

Context7

Codebase Memory

Exa

作者的 README

AI Guardian

Supported runtimes

What it does

Key features

What this tool does, and does not, decide

Capability matrix (21 MCP tools)

Reads (11)

Writes (8)

Undo (2)

Quick start

As a Claude Code plugin

As an OpenClaw plugin

As a CLI or standalone MCP server