Auth Your Agent runs on your own machine — the client starts it, so there is no endpoint to ping. 3 782 installs a week from pypi. Last commit 14 Oct 2026.
Act for a person on websites: sandboxed browser, phone approvals, saved logins, scheduled plans.
We read the source, 1 d ago · rules ccca72095570
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.
r = subprocess.run(["docker", *args], capture_output=capture, text=True)
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
const pyOut = JSON.parse(execFileSync(PY, ["-c", `
"sig2=:gHzpLNeHaHIO19NaJH9YMW5dcVSi2s0wOMBr6p18vcofS106sfC4KBIS0/szPlBBd1vIcyQ88B6CTEWIhRAiVrb9zfX0mx1aG12CSGWcYkSirHeyTxhbuJvXd27ed6skWoy4PjXItq38936ivUQjfdIwXh1aX6HxkAC3vRnEdSNfntkLWeEuIQ5BLIOBGE39fSwg27Qjq6OVWYas/9/aFUr3HA34MXWYdp+//cvlEKDp3kRoLOw9ro0AOr6srHrTeEtxon2afcws1…
const child = spawn(cmd, [], {
r = subprocess.run(cmd, shell=True, capture_output=True, text=True)
start, end = src.index("E = {"), src.index("for name, (agent, si_, sg_) in E.items():")
exec(src[start:end], {"unwrap": unwrap}, ns)
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 mcp -- uvx authyouragent
{
"mcpServers": {
"mcp": {
"args": [
"authyouragent"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp]
command = "uvx"
args = ["authyouragent"]
{
"mcpServers": {
"mcp": {
"args": [
"authyouragent"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp": {
"args": [
"authyouragent"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
AYA_AGENT_ID (Your agent's id (ag_...), from Agents in the Auth Your Agent app), AYA_KEY_FILE (Path to the agent's private key (PEM), created with: authyouragent keygen), AYA_VAULT_URL (Browser vault address), AYA_VAULT_TOKEN_FILE (Path to the vault's token file).
The author declared them in the registry entry; get the values from the project itself.
Isolated browsers with a persistent identity for AI agents, on your own Windows machine.
Websites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.
Rove — supervised browser for AI agents. Your agent drives; a human watches, takes over.
Publish, test and share browser games on PlayDrop from your AI agent.
A real browser for your agent: a page to clean text for $0.009, a 25-page site for $0.14. x402.
Client intake: files, copy and logins from clients, from the browser or your AI agent.
A real Safari-engine (WebKit) browser for agents on macOS: sessions, extraction, bot checks.
Your own signed-in Mac browser for any agent: open, read and act in tabs. Local and free.
Answers built from our own checks of this server.