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/airas-org/airasWrote 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/airas-org/airas/airas-airas)<a href="https://agentmods.dev/mcp/airas-org/airas/airas-airas"><img src="https://agentmods.dev/badge/mcp/airas-org/airas/airas-airas/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/airas-org/airas/airas-airas"><img src="https://agentmods.dev/badge/mcp/airas-org/airas/airas-airas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
Grade A, and why
airas 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 yesterday.
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
{
"airas": {
"command": "uvx",
"args": [
"airas==0.4.0"
]
}
}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.
- yesterday Changed · -2 lines e3d7fdde0461
- 7d ago Changed · +2 lines 29ca390ca9db
- 11d ago First seen · 8 lines scan A e6aba547163a
airas is an MCP server published in the GitHub repository airas-org/airas (35 stars, last pushed yesterday), 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 2026-08-30.
Other mcp servers, from other repositories
notebooklm
NotebookLM research automation — CLI, MCP server, and Claude Code Skill. Runs locally from the notebooklm-skill Python package.
prove
MCP server "prove" as configured in whenpoem/aiscientist. Launched with uv tool run --from claudescientist[all]==5.1.4 claudescientist mcp prove.
hn-tech-signal-mcp
MCP server for tech & AI intelligence – aggregates HackerNews, arXiv, Lobste.rs and GitHub. No API key required. Runs locally from the hn-tech-signal-mcp Python package.
arxiv-research-mcp
An MCP server exposing arXiv research tools (search, abstracts, author lookup, trending) to LLM agents. Runs locally from the arxiv-research-mcp Python package.
sequential-thinking
Adds a structured step-by-step reasoning tool the agent can call to break a problem into revisable thoughts. Runs locally from the @modelcontextprotocol/server-sequential-thinking npm package.
github
Lets the agent work with GitHub: search code, read and create issues and pull requests, and manage repositories through the GitHub API. Runs locally from the @modelcontextprotocol/server-github npm package.