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/yywz2026-coder/AgentAirlockInstalling this writes the configuration, not the program: `<ABSOLUTE_NODE_EXE>` has to be on your PATH already, or the server will not start.
Wrote 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/yywz2026-coder/agentairlock/claude-code-agentairlock)<a href="https://agentmods.dev/mcp/yywz2026-coder/agentairlock/claude-code-agentairlock"><img src="https://agentmods.dev/badge/mcp/yywz2026-coder/agentairlock/claude-code-agentairlock/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/yywz2026-coder/agentairlock/claude-code-agentairlock"><img src="https://agentmods.dev/badge/mcp/yywz2026-coder/agentairlock/claude-code-agentairlock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentairlock 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 2mo 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
{
"agentairlock": {
"command": "<ABSOLUTE_NODE_EXE>",
"args": [
"<AGENTAIRLOCK_ROOT>\\integrations\\claude-code\\adapter\\index.mjs",
"--identity-file",
"<AGENTAIRLOCK_ROOT>\\data\\adapters\\claude-code.json"
]
}
}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.
- 2mo ago First seen · 10 lines scan A 05e8d9f57501
agentairlock is an MCP server published in the GitHub repository yywz2026-coder/AgentAirlock (0 stars, last pushed 3mo ago), licensed Apache-2.0. 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
openflowkit-mcp
Local-first OpenFlowKit diagramming tools for Claude, Cursor, Windsurf & other MCP clients. Runs locally from the @vrun-design/openflowkit-mcp npm package.
remnic
MCP server "remnic", hosted remotely at localhost, as configured in joshuaswarren/remnic.
flameox
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks. Runs locally from the flameox Python package.
mcp
Memory the human governs, on their own machine, plus what other coding agents here wrote. Runs locally from the @mnemosyne_os/mcp npm package. Needs 3 environment variables to run.
rag-rat
CLI and MCP entrypoint for indexing repositories into local source, graph, history, and memory evidence. Runs locally from the @rag-rat/bin npm package.
llm-usage-mcp
Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP. Runs locally from the llm-usage-mcp Python package.