GitHub
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
Description from the maker (original English)
eBPF network observability and safe emergency control for Linux and Kubernetes.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
NETRA_URL, NETRA_API_KEY, NETRA_MCP_ALLOW_MUTATIONS, NETRA_MCP_ACTORValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"netra": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"NETRA_URL",
"-e",
"NETRA_API_KEY",
"-e",
"NETRA_MCP_ALLOW_MUTATIONS",
"-e",
"NETRA_MCP_ACTOR",
"ghcr.io/zyvorai/netra-mcp:0.32.0"
],
"env": {
"NETRA_URL": "your-value",
"NETRA_API_KEY": "your-value",
"NETRA_MCP_ALLOW_MUTATIONS": "your-value",
"NETRA_MCP_ACTOR": "your-value"
}
}
}
}Run this in your terminal
claude mcp add netra --env NETRA_URL=your-value --env NETRA_API_KEY=your-value --env NETRA_MCP_ALLOW_MUTATIONS=your-value --env NETRA_MCP_ACTOR=your-value -- docker run -i --rm -e NETRA_URL -e NETRA_API_KEY -e NETRA_MCP_ALLOW_MUTATIONS -e NETRA_MCP_ACTOR ghcr.io/zyvorai/netra-mcp:0.32.0Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"netra": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"NETRA_URL",
"-e",
"NETRA_API_KEY",
"-e",
"NETRA_MCP_ALLOW_MUTATIONS",
"-e",
"NETRA_MCP_ACTOR",
"ghcr.io/zyvorai/netra-mcp:0.32.0"
],
"env": {
"NETRA_URL": "your-value",
"NETRA_API_KEY": "your-value",
"NETRA_MCP_ALLOW_MUTATIONS": "your-value",
"NETRA_MCP_ACTOR": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"netra": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"NETRA_URL",
"-e",
"NETRA_API_KEY",
"-e",
"NETRA_MCP_ALLOW_MUTATIONS",
"-e",
"NETRA_MCP_ACTOR",
"ghcr.io/zyvorai/netra-mcp:0.32.0"
],
"env": {
"NETRA_URL": "your-value",
"NETRA_API_KEY": "your-value",
"NETRA_MCP_ALLOW_MUTATIONS": "your-value",
"NETRA_MCP_ACTOR": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
NETRA_MCP_ALLOW_MUTATIONS envNETRA_MCP_ACTOR envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account zyvorai, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: NETRA_URL, NETRA_API_KEY
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.32.0) reached the registry 19 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Docker on your computer.
In the same category: GitHub, Desktop Commander, Cloudflare MCP
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.
MCP server for terminal commands, file operations, and process management
Cloudflare MCP servers
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Standalone eBPF network observability and emergency network control for Linux/Kubernetes — with optional Cilium + Hubble enrichment. Kernel drop attribution, path and congestion diagnostics, live packet capture, and leased deny rules that return to observe on their own, on any CNI.
Observe-first · Lease-bounded, fails open · No CNI required · No payload collection · 190 MCP tools
📖 [Read the full docs](https://zyvorai.github.io/zyvor-netra/) — quickstart, architecture, security model, and a product tour.
From CHANGELOG.md (0.28.2 to 0.30.0):
| Per-second metrics *(0.30.0)* | Host, network, cgroup, process-group, eBPF and workload RED series every second, with anomaly detection, metric alerts, app collectors, exporters, and a link from any chart spike to the flows and drops behind it. Docs → |
| Node isolation *(0.30.0)* | A per-node allow-only egress filter in shadow (count what it would block) or enforce, as a standalone TCX program. Docs → |
| Security review *(0.30.0)* | DNS query types, versioned threat feeds with expiry, rollback and optional HTTPS refresh, deny-predicate overlap review and exact-workload incident correlation. Docs → |
| L7 metadata on current kernels *(0.30.0)* | TLS SNI, HTTP Host and DNS names load again on Linux 6.8+ (they were rejected by the verifier), using bpf_loop on Linux 5.17+. Docs → |
| Netlink change recorder | Which link, address, route or neighbor changed on a node, and when, across every routing table. Docs → |
| Netlink findings and alerts | Default route removed, gateway unreachable, uplink down, MTU changed, derived from the recorded changes. |
| Who made the change | An fentry on rtnetlink_rcv_msg attributes each modifying netlink request to the process that sent it. |
| BPF attachment inventory | Netra notices when its own hooks have silently gone, for example after a NIC or bond is recreated. Docs → |
| One UX contract | Dashboard and docs site follow one design contract; Apple light by default, dark one click away. |
| Stable controller certificate | tls.existingSecret serves a kubernetes.io/tls Secret so clients can pin the controller certificate. |
| When this happens… | Netra gives you… |
|---|---|
| Traffic disappears and nobody can say where | Kernel drop attribution: the connection, the reason, and the kernel function that dropped it |
| You need to act now, but enforcement is scary | Leased deny that reverts by itself, previewed against live traffic first |
| Your CNI is not Cilium, or you cannot change it | cgroup v2 hooks that work on any CNI, with no kernel module and no app changes |
| "The network is slow" with no evidence | TCP path diagnostics and a Congestion Map that colors every layer of the Linux network stack by its worst finding |
| A chart spiked and you need to know why | Per-second metrics with anomaly detection, where every spike links to the flows, drop reasons and captures from that window |
| You need packets from one node, now | Filtered, time-bounded live capture with a Wireshark-style layered decode, one click from a finding |
| Your AI agent should investigate without breaking things | An MCP server with 190 tools; mutations stay behind NETRA_MCP_ALLOW_MUTATIONS |
Netra does not require Cilium. The node agent owns its own programs and maps below /sys/fs/bpf/netra. If Cilium/Hubble exists, Netra can manage CiliumNetworkPolicy and display Hubble flows, but both integrations are opt-in.
| Netra | Cilium + Hubble | |
|---|---|---|
| What it is | Observability and emergency control that runs next to your CNI | A CNI with Hubble observability built on its datapath |
| Adoption | Helm install of a controller and a node agent DaemonSet; no CNI change | Cilium becomes the cluster's CNI |
| Kernel hooks | cgroup skb, connect/sendmsg, sockops; optional kfree_skb, TCX and XDP | Cilium's own eBPF datapath |
| Enforcement model | Leased deny that returns to observe when the lease expires or the controller loses state | Network policies persist until removed |
| Drop diagnosis | Kernel drop reason and dropping function per connection, plus Drop Explain | Hubble flow verdicts and drop reasons from the Cilium datapath |
| Plain Linux hosts | The same agent and hooks | Built around Cilium-managed networking |
| Works together | Optional CiliumNetworkPolicy authoring and Hubble Relay flows | — |
| Choose Cilium + Hubble when | You want a full CNI with policy enforcement and Hubble observability built in, and can make it your CNI |
Netra never modifies or pins over Cilium-owned BPF maps, so the two can share a cluster.
Overview, the Firewall page's unified rules table and NetPol v2 allow-list, then a real in-browser VNC console connected to a running KubeVirt VM — captured against a live lab deployment, not a mockup:
*The Overview page.* More screens follow in Observe, Diagnose and Contain.
Browser / netractl
| v +---------------------+ | netrad | | API + UI + state | +----------+----------+ | desired config| node reports v +------------------------------------------------+ | netra-agent on every Linux node | | | | cgroup skb + socket hooks optional TCX | | | optional XDP | | +------ Netra maps/ring buffer ------+ | /sys/fs/bpf/netra | +------------------------------------------------+
netrad serves HTTPS on :30870 by default. Hook model, visibility boundaries and the optional Cilium/Hubble integration: docs/architecture.md · Standalone eBPF.
make install # netractl → /usr/local/bin (or PREFIX=$HOME/.local)
netractl install --namespace netra-system # Helm install: controller + node agent DaemonSet netractl status
Then open https:// :30870 and sign in. The dashboard sits behind a login screen — see Signing in (the nav bar and login screen carry the Zyvor mark).
Requires Linux with cgroup v2 and bpffs; practical baseline Linux 5.8+ (TCX 6.6+). Run netra-doctor first. Full steps, Helm values, Cilium/Hubble and CLI examples: [Install guide](docs/install.md).
Flows with pod and owner attribution, TCP health, DNS, TLS SNI and HTTP Host metadata, behavior baselines and drift. Live Hubble flows when Cilium is present. Capabilities →
TCP path diagnostics measure connect latency and transport pressure per workload, plus edge-observed handshake and RTT histograms that see NAT'd flows. Path → · Edge intel →
Congestion Map colors every layer of the Linux network stack by its worst finding, cluster-wide. One click jumps to a capture on the offending node. Kernel diagnostics →
Packet Capture streams a filtered, time-bounded capture live, color-coded by protocol, with a Wireshark-style layered decode and hex dump. Opt-in auto-capture persists PCAPs on critical findings. Capture →
A Congestion Map finding to a live, decoded, color-coded capture on the offending node:
Drop Explain answers "why was this dropped?" with kernel reasons and policy context. Drop diagnostics → · Drop info →
More: DNS, ICMP, behavior and rate insights.
Per-second metrics, zero config. Every node streams host, network stack, conntrack, cgroup, process-group, eBPF datapath and per-workload RED series to the controller, kept at 1 s for an hour, 1 min for two weeks and 1 h for a year. The Metrics page charts every context live, with an anomaly ribbon on each chart. Metrics →
Only the beginning is shown; read the rest in the repo