Air runs on your own machine — the client starts it, so there is no endpoint to ping. 76 installs a week from npm. Last commit 31 Mar 2026.
AI-optimized tool output compression for read, grep, diff, bash, test, web, search, and more
What the code does
We read the source, 5 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
? spawnSync(command[0], {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add air -- npx -y @10iii/air-mcp-server{
"mcpServers": {
"air": {
"command": "npx",
"args": [
"-y",
"@10iii/air-mcp-server"
]
}
}
}[mcp_servers.air]
command = "npx"
args = ["-y", "@10iii/air-mcp-server"]{
"mcpServers": {
"air": {
"command": "npx",
"args": [
"-y",
"@10iii/air-mcp-server"
]
}
}
}{
"servers": {
"air": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@10iii/air-mcp-server"
]
}
}
}Alternatives to Air
same job, measured the same waySnapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
Search, read, download and report on tested step-by-step recipes (playbooks) for AI agents.
Regression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.
Create and control browser sessions for web automation, testing, and AI agent tasks
Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.
Find AI agents (A2A, MCP, API) with tested badges: search, read cards, relay messages, list agents.
32 free MCP tools for data validation, text optimization, and synthetic test data.
Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.
Air — questions
Answers built from our own checks of this server.