Physverify runs on your own machine — the client starts it, so there is no endpoint to ping. 1 090 installs a week from pypi. Last commit 1 Nov 2026.
Runs physverify checks on physics code. It runs the code it checks: use on trusted code only.
We read the source, 1 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.
exec(compile(ast.Module(body=body, type_ignores=[]), str(path), "exec"), module.__dict__)
p = subprocess.run([sys.executable, script.name], cwd=script.parent, stdin=subprocess.DEVNULL,
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 physverify -- uvx physverify
{
"mcpServers": {
"physverify": {
"command": "uvx",
"args": [
"physverify"
]
}
}
}
[mcp_servers.physverify]
command = "uvx"
args = ["physverify"]
{
"mcpServers": {
"physverify": {
"command": "uvx",
"args": [
"physverify"
]
}
}
}
{
"servers": {
"physverify": {
"type": "stdio",
"command": "uvx",
"args": [
"physverify"
]
}
}
}
Read-only tools that check whether code, and the tests that claim it works, are real.
21 dated checks over SPF, DKIM, DMARC, RFC 8058 one-click unsubscribe and TLS, in VS Code and in the
Checks ML model files (pickle, PyTorch, joblib, NumPy, GGUF, ONNX) for code that runs on load.
Checks AI-written SvGrid code against the real API, plus version-pinned Svelte 5 grid docs.
24 checks on the register CSV before it reaches the supervisor — LEI check digits, ISO dates and cod
Free live-app check by an AI agent. On request it fixes the code and tests the app again.
Core Web Vitals (LCP, INP, CLS) per URL from the Chrome UX Report, with daily checks on Pro.
Returns only the unit tests affected by your current Kotlin/Android code changes.
Answers built from our own checks of this server.