AdminKit runs on your own machine — the client starts it, so there is no endpoint to ping. 2 303 installs a week from pypi. Last commit 1 Nov 2026.
Network, DNS, mail-auth and MCP endpoint security checks for AI agents, backed by adminkit.net.
Today is the operative word: we check AdminKit every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 adminkit-mcp -- uvx adminkit-mcp
{
"mcpServers": {
"adminkit-mcp": {
"command": "uvx",
"args": [
"adminkit-mcp"
]
}
}
}
[mcp_servers.adminkit-mcp]
command = "uvx"
args = ["adminkit-mcp"]
{
"mcpServers": {
"adminkit-mcp": {
"command": "uvx",
"args": [
"adminkit-mcp"
]
}
}
}
{
"servers": {
"adminkit-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"adminkit-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
ADMINKIT_API_KEY (Optional AdminKit API key (explain_report, higher limits)).
Security for AI agents: MCP audits, secret redaction, skill vetting, network scans, agent checkout.
Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend
Intent security pre-flight checks for autonomous AI agents.
Read-only network & security recon tools (DNS, TLS, headers, CORS) for AI agents, each graded.
kube-linter audit for Kubernetes manifests — 63 checks: security, availability, RBAC, network.
License check, outdated deps, security for AI agents
Security audit for AI agents: code, deps, exposure, secrets, drift, SBOM, and IoC.
Paid email, DNS, mail-security and RDAP intelligence for agents over x402.
Answers built from our own checks of this server.