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/michaelahern/airthings-consumer-mcpWrote 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/michaelahern/airthings-consumer-mcp/airthings-consumer-mcp)<a href="https://agentmods.dev/mcp/michaelahern/airthings-consumer-mcp/airthings-consumer-mcp"><img src="https://agentmods.dev/badge/mcp/michaelahern/airthings-consumer-mcp/airthings-consumer-mcp/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/michaelahern/airthings-consumer-mcp/airthings-consumer-mcp"><img src="https://agentmods.dev/badge/mcp/michaelahern/airthings-consumer-mcp/airthings-consumer-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
airthings-consumer-mcp 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 7d 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
{
"airthings-consumer-mcp": {
"command": "npx",
"args": [
"airthings-consumer-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.
- 7d ago First seen · 8 lines scan A f0421751e6e4
airthings-consumer-mcp is an MCP server published in the GitHub repository michaelahern/airthings-consumer-mcp (0 stars, last pushed 5d ago), licensed ISC. 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 2026-09-01.
Other mcp servers, from other repositories
ros-mcp-server
Connect AI Language Models with Robots on ROS using MCP. Runs locally from the ros-mcp Python package.
unifi-access-mcp
UniFi Access MCP Server. Runs locally from the unifi-access-mcp Python package. Needs 6 environment variables to run.
unifi-network-mcp
Unifi Network MCP Server. Runs locally from the unifi-network-mcp Python package. Needs 7 environment variables to run.
unifi-protect-mcp
UniFi Protect MCP Server. Runs locally from the unifi-protect-mcp Python package. Needs 6 environment variables to run.
scrcpy-mcp
MCP server for Android device control via ADB and scrcpy. Runs locally from the scrcpy-mcp npm package. Needs 3 environment variables to run.
librenms-mcp
MCP server for LibreNMS management. Runs locally from the librenms-mcp Python package. Needs 13 environment variables to run.