Paqtra

Name: Paqtra
Author: zyvorai

作者：zyvorai版本 2.2.3i★ –i在你的电脑上运行

注册名称io.github.zyvorai/paqtra

安装

概览

作者提供的说明（英文原文）

Read-only Cilium and Hubble network observability and flow investigation for Kubernetes.

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非常新★ –

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: 开发者工具
你需要填写：PAQTRA_URL, PAQTRA_TOKEN, PAQTRA_PASSWORD

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： PAQTRA_URL, PAQTRA_TOKEN, PAQTRA_USERNAME, PAQTRA_PASSWORD

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

Docker已安装 Docker

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": {
    "paqtra": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PAQTRA_URL",
        "-e",
        "PAQTRA_TOKEN",
        "-e",
        "PAQTRA_USERNAME",
        "-e",
        "PAQTRA_PASSWORD",
        "ghcr.io/zyvorai/paqtra-mcp:2.2.3"
      ],
      "env": {
        "PAQTRA_URL": "your-value",
        "PAQTRA_TOKEN": "your-value",
        "PAQTRA_USERNAME": "your-value",
        "PAQTRA_PASSWORD": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add paqtra --env PAQTRA_URL=your-value --env PAQTRA_TOKEN=your-value --env PAQTRA_USERNAME=your-value --env PAQTRA_PASSWORD=your-value -- docker run -i --rm -e PAQTRA_URL -e PAQTRA_TOKEN -e PAQTRA_USERNAME -e PAQTRA_PASSWORD ghcr.io/zyvorai/paqtra-mcp:2.2.3

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": {
    "paqtra": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PAQTRA_URL",
        "-e",
        "PAQTRA_TOKEN",
        "-e",
        "PAQTRA_USERNAME",
        "-e",
        "PAQTRA_PASSWORD",
        "ghcr.io/zyvorai/paqtra-mcp:2.2.3"
      ],
      "env": {
        "PAQTRA_URL": "your-value",
        "PAQTRA_TOKEN": "your-value",
        "PAQTRA_USERNAME": "your-value",
        "PAQTRA_PASSWORD": "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": {
    "paqtra": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "PAQTRA_URL",
        "-e",
        "PAQTRA_TOKEN",
        "-e",
        "PAQTRA_USERNAME",
        "-e",
        "PAQTRA_PASSWORD",
        "ghcr.io/zyvorai/paqtra-mcp:2.2.3"
      ],
      "env": {
        "PAQTRA_URL": "your-value",
        "PAQTRA_TOKEN": "your-value",
        "PAQTRA_USERNAME": "your-value",
        "PAQTRA_PASSWORD": "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

PAQTRA_URL 必填 env
Base URL of the Paqtra API, for example https://paqtra.example:9191.
PAQTRA_TOKEN 机密 env
JWT bearer token for the Paqtra API. Alternative to PAQTRA_USERNAME and PAQTRA_PASSWORD.
PAQTRA_USERNAME env
Paqtra user to log in as when PAQTRA_TOKEN is not set. A read-only role is enough.
PAQTRA_PASSWORD 机密 env
Password for PAQTRA_USERNAME.

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9日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 zyvorai 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“开发者工具”中的其他服务器比较i

星标数多于此分类中其他 5566 个服务器的 0%
发布到注册中心的时间比此分类中其他 5566 个服务器的 55% 更新
基础检查结果等于或优于此分类中其他 5566 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

Paqtra 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：PAQTRA_URL, PAQTRA_TOKEN, PAQTRA_PASSWORD

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（2.2.3）于24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 Docker。

有什么可以替代它？

同一分类中有：GitHub, Desktop Commander, Cloudflare 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：↓ 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

GitHub

Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.

作者：github广泛使用★ 3.4万5天前更新

电脑或云端

安装

Desktop Commander

MCP server for terminal commands, file operations, and process management

作者：wonderwhy-er广泛使用↓ 71万/周★ 1万18天前更新

在你的电脑上运行

安装

Cloudflare MCP

Cloudflare MCP servers

作者：cloudflare广泛使用★ 444614个月前更新

在云端运行✓ mcp.cloudflare.com

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。

Paqtra

Why can't A reach B? Paqtra traces every flow and shows Cilium's verdict.

Cilium-native network observability and operations for Kubernetes. Every Hubble flow stored and searchable, drops explained by Cilium reason, CiliumNetworkPolicy changes simulated before you apply them, and enforcement left with Cilium.

Web dashboard · REST API · Terminal TUI · Why denied? on any flow · Read-only toward the datapath · Free, Apache 2.0

📖 [Read the full docs](https://zyvorai.github.io/zyvor-paqtra/): quickstart, architecture, the Cilium boundary, and a product tour.

What's new


Per-second metrics platform (Unreleased)	Every agent streams host, network, disk, pod, process-group and app metrics each second; the API keeps them in 1 s / 1 min / 1 h tiers, adds Hubble flow, verdict, drop, HTTP and DNS series, flags anomalies per dimension, runs 45 built-in metric alerts and exports to Prometheus remote write, OTLP or Graphite. docs/metrics.md
MCP server (2.2.3)	`paqtra-mcp`, a read-only stdio MCP server with 39 tools, lets an AI agent query a Paqtra deployment with the caller's own credentials. Published from the v2.2.3 release as `ghcr.io/zyvorai/paqtra-mcp:2.2.3` and to the MCP Registry as `io.github.zyvorai/paqtra`. docs/mcp-integration.md
Installs like `cilium-cli` (2.2.0)	The Helm chart is compiled into the `paqtra` binary: `install`, `upgrade`, `status --wait`, `--with-cilium`, prerequisite checks, `doctor`.
Signed releases (2.2.0)	Static musl Linux and macOS binaries with `sha256sums.txt`, a cosign keyless signature, an SBOM and a Homebrew formula.
Rule-level policy editing (2.2.0)	Add, replace or delete one rule of a `CiliumNetworkPolicy`, with `?dry_run=true`, conflict detection and audit entries.
Cilium Insights (2.2.0)	Read-only views of Cilium features, Hubble nodes, BGP, LB-IPAM, L2, pod IP pools, CIDR groups and Gateway API resources.
Change impact and shareable investigations (2.2.0)	Before/after flow correlation for a change, and investigation bundles with a time-limited, redacted share link.
Why denied? (2.1.0)	From any dropped flow: identities, candidate CNP/CCNP, the drop reason and a draft allow.
Large flow stores stay fast (2.2.1, 2.2.2)	Reads never block ingest, every read has a deadline, and recent-window queries go through the time index.

Full history: CHANGELOG.md.

Why Paqtra

When this happens…	Paqtra gives you…
A request fails and nobody knows why	Path explain and Why denied? on any flow, with confidence-tagged evidence
Cilium drops packets and the reason is buried	Drop analytics by Cilium reason, plus a per-packet explanation
You want to change policy without breaking things	Simulate a `CiliumNetworkPolicy` against indexed flows before you apply it
The flow you need scrolled out of Hubble minutes ago	A continuous Hubble follow-stream into a local SQLite flow store, queried by time window
Network tooling that touches the datapath is a non-starter	Read-only toward Cilium: no BPF map writes, no program attach, not a second CNI
Every Cilium add-on needs its own install story	`paqtra install` with the Helm chart built in, `paqtra status --wait`, `paqtra doctor`

Paqtra is observe-first. Flows come from Hubble; node-local enrichment may read the BPF map inventory. Enforcement stays with Cilium: policy changes go through CiliumNetworkPolicy (CNP), never through Paqtra's own datapath.

Paqtra vs Hubble UI

Paqtra does not replace Hubble; it reads Hubble's flows through Hubble Relay and builds on them.

	Paqtra	Hubble UI (ships with Cilium)
Flow source	Hubble Observer gRPC follow-stream	Hubble Relay
Flow history	Local SQLite flow store, queried by time window	Live flows from Hubble's in-memory buffers
Service map	Service map and observed-traffic topology	Service map per namespace
"Why can't A reach B?"	Path explain with observed / inferred / unavailable evidence	Inspect the flows yourself
Drops	Drop analytics by Cilium reason, Why denied? per flow	Verdict and drop reason on each flow
Policy	Rule builder, YAML editor, AutoPolicy, simulate, apply as CNP	Not a policy editor
Interfaces	Web dashboard, REST API, terminal UI, CLI	Web UI (plus the `hubble` CLI)
Choose Hubble UI when		Live flows and a service map are all you need and you want only what ships with Cilium

See it live

Captured against a live lab cluster with Cilium and Hubble. Full tour on the docs site gallery.

Observe

Live Hubble flows with verdict coloring and WebSocket streaming, a service map and an observed-traffic topology built from real flows. Real L7 DNS query/rcode/latency when Cilium DNS visibility is on; L4-only never invents SERVFAIL. Capabilities →

Per-second node metrics next to the flows: CPU, memory, disks, interfaces, TCP, conntrack, pod cgroups, process groups (by comm only) and annotated apps (nginx, Redis, Envoy, CoreDNS, etcd, any Prometheus endpoint), with live canvas charts, per-dimension anomaly detection, "what changed here?" correlation and Netdata-style metric alerts that notify but never apply policy. paqtra metrics … covers the same from the terminal. Metrics → · Alerts → · Anomalies → · Apps →

Investigate

Ask "why can't A reach B?" and get an answer with observed, inferred or unavailable evidence labels. Click Why denied? on any dropped flow. Investigate → · Root cause →

The dashboard also includes real kernel eBPF data views powered by bpftool: conntrack tables, policy maps, IP cache, LB maps and drop analytics. All read-only. eBPF integration →

Secure

A visual rule builder, a YAML editor, ML-powered AutoPolicy and an evidence-backed simulator, all applied as CiliumNetworkPolicy through the Kubernetes API. Cilium enforces. AutoPolicy → · Simulator →

Also included: compliance audits (CIS, NIST, SOC 2), anomaly detection, chaos engineering, canary deployments and multi-cluster views. Everything Paqtra does →

MCP

paqtra-mcp is a stdio Model Context Protocol server that lets an AI agent (Claude Desktop, Hermes Agent, any MCP client) read a running Paqtra deployment. It exposes 39 tools, all read-only with respect to the cluster: no policy apply, edit or delete, no chaos, no healer fix, no cluster sync, no flow-store purge. The two investigate tools store an evidence bundle in the API and nothing else. Every call is made with your own API credentials, so RBAC and namespace scoping apply.

Registry name: io.github.zyvorai/paqtra (published from the v2.2.3 release)
Image: ghcr.io/zyvorai/paqtra-mcp:2.2.3
Configuration: PAQTRA_URL, plus PAQTRA_TOKEN or PAQTRA_USERNAME / PAQTRA_PASSWORD; use a viewer-role account.

Setup, tool scope and the protocol: docs/mcp-integration.md.

How it fits together

Component	Port	Role
API (`ghcr.io/zyvorai/paqtra-api`)	`9191`	Rust + Axum REST API: Hubble ingest into the flow store, investigate, drops, policy, JWT auth
UI (`ghcr.io/zyvorai/paqtra-ui`)	`8443`	React dashboard, served over TLS by default
Node agent (`ghcr.io/zyvorai/paqtra`)	`9192`	DaemonSet on every node: health and read-only map and program inventory
`paqtra` CLI	—	Install, upgrade, status, doctor, `ui`, `hubble enable`; the Helm chart is built in

Ports are the Helm chart defaults in chart/values.yaml. Architecture in depth: docs/architecture.md · docs/web-architecture.md.

What Paqtra never does

Hard boundaries, enforced by review and repeated in AGENTS.md:

Never writes Cilium BPF maps or pins over cil_* programs.
Never attaches, detaches or replaces Cilium (or Netra) programs. Attachment inventory is read-only classification (cil_* / netra_* / other).
The agent observes, reports health and inventories. Policy apply goes through Cilium CRDs.
Does not collect application payloads, argv/cmdline, or Secret contents.
Does not introduce a second CNI or compete with Cilium's datapath.
Prefers Hubble for flows; uses maps for node-local enrichment only.

Details: docs/cilium-brotherhood.md and docs/ebpf-integration.md.

Quickstart

Prerequisites: a Kubernetes cluster and a kube-context. Cilium with Hubble Relay is required too; paqtra install --with-cilium sets it up if it is missing.

# Install the CLI (downloads, verifies and installs the latest release)

curl -fsSL https://raw.githubusercontent.com/zyvorai/paqtra/main/install.sh | sh # or: brew install zyvorai/tap/paqtra

Install Paqtra into the current kube-context (the Helm chart is built in)

paqtra install # add --with-cilium if the cluster has no Cilium yet paqtra status --wait paqtra ui # open the console

Something wrong?

paqtra doctor

Build from source, Docker, Helm, environment variables and testing: [Install guide](docs/install.md) · CLI reference: docs/cli.md.

Paqtra vs PacketWolf

![Paqtra

只显示了开头部分；其余内容请在仓库中阅读

Paqtra

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

需要你填写的值

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“开发者工具”中的其他服务器比较i

常见问题

替代选择

GitHub

Desktop Commander

Cloudflare MCP

作者的 README

Paqtra

Why can't A reach B? Paqtra traces every flow and shows Cilium's verdict.

What's new

Why Paqtra

Paqtra vs Hubble UI

See it live

Observe

Investigate

Secure

MCP

How it fits together

What Paqtra never does

Quickstart

Install Paqtra into the current kube-context (the Helm chart is built in)

Something wrong?

Paqtra vs PacketWolf