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/coltonbearden/carrelWrote 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/coltonbearden/carrel/carrel-agent-carrel)<a href="https://agentmods.dev/mcp/coltonbearden/carrel/carrel-agent-carrel"><img src="https://agentmods.dev/badge/mcp/coltonbearden/carrel/carrel-agent-carrel/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/coltonbearden/carrel/carrel-agent-carrel"><img src="https://agentmods.dev/badge/mcp/coltonbearden/carrel/carrel-agent-carrel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
carrel 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 10d 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
{
"carrel": {
"command": "carrel",
"args": [
"mcp"
]
}
}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.
- 10d ago First seen · 8 lines scan A 01b11eeb2d90
carrel is an MCP server published in the GitHub repository coltonbearden/carrel (1 stars, last pushed today), licensed MIT. 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 2026-08-31.
Other mcp servers, from other repositories
rarcane
MCP server and CLI for Arcane: manage Docker containers, images, networks, volumes, and Compose projects over stdio or streamable HTTP, with auth. Runs locally from the @dinglebear/rarcane npm package. Needs 9 environment variables to run.
rarcane
Arcane Docker and Compose management over MCP and CLI with authenticated stdio and HTTP. Runs locally from the @dinglebear/rarcane npm package. Needs 6 environment variables to run.
tailscale
MCP server and CLI for Tailscale: inspect and manage tailnet devices, routes, users, keys, DNS, and ACL policy over stdio or streamable HTTP. Runs locally from the @dinglebear/rtailscale npm package. Needs 10 environment variables to run.
rtailscale
Tailscale device, route, DNS, key, user, and ACL management over MCP and CLI. Runs locally from the @dinglebear/rtailscale npm package. Needs 5 environment variables to run.
unifi
MCP server and CLI for UniFi Network controllers: clients, devices, WLANs, firewall, and health over stdio or streamable HTTP, with auth. Runs locally from the @dinglebear/runifi npm package. Needs 12 environment variables to run.
runifi
Rust MCP server and CLI for UniFi Network controller operations. Runs locally from the @dinglebear/runifi npm package. Needs 6 environment variables to run.