Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/ArthurVardevanyan/HomeLabWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/arthurvardevanyan/homelab/scafctl)<a href="https://agentmods.dev/mcp/arthurvardevanyan/homelab/scafctl"><img src="https://agentmods.dev/badge/mcp/arthurvardevanyan/homelab/scafctl/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/arthurvardevanyan/homelab/scafctl"><img src="https://agentmods.dev/badge/mcp/arthurvardevanyan/homelab/scafctl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
scafctl scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"scafctl": {
"type": "stdio",
"command": "scafctl",
"args": [
"mcp",
"serve"
]
}
}What else mcp.json configures
This page is one entry in a file that holds 3. Installing the file brings all of them; each is measured and scanned on its own page.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 10 lines scan A cba633a280b2
scafctl is an MCP server published in the GitHub repository ArthurVardevanyan/HomeLab (21 stars, last pushed yesterday), licensed Unlicense. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other mcp servers, from other repositories
WhiteCapData-Dev
WhiteCapData-Dev — an MCP server to operate a k3s / Kubernetes cluster (health, logs, and guarded restart/scale/delete) straight from your AI agent. Runs locally from the whitecapdata-dev Python package. Needs 4 environment variables to run.
kubernetes-mcp-server
A Model Context Protocol (MCP) server for Kubernetes and OpenShift. Runs locally from the kubernetes-mcp-server npm package.
homelab-monitor
MCP server "homelab-monitor" as configured in SikamikanikoBG/homelab-monitor. Runs in Docker (docker.io/sikamikaniko123/homelab-monitor:0.14.2). Needs 2 environment variables to run.
victoriametrics
MCP server "victoriametrics" as configured in Smana/cloud-native-ref. Launched with /usr/local/bin/mcp-victoriametrics. Needs 2 environment variables to run.
mikromcp
MCP server for MikroTik RouterOS: typed tools, dry-run, RBAC, audit logs, and rollback. Runs locally from the mikromcp npm package. Needs 3 environment variables to run.
langgraph-agent
MCP server "langgraph-agent" as configured in vishnu2kmohan/mcp-server-langgraph. Runs mcp_server_langgraph.mcp.server_stdio with python. Needs 1 environment variable to run.