CookieGuard runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 7 Nov 2026.
Audit HTTP cookie security against your local policy. Returns findings without cookie values.
We read the source, 21 h ago · rules 995398eba69f
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.
d = pickle.load(f)
'node': subprocess.check_output([os.environ.get('COOKIEGUARD_NODE', 'node'), '--version'], text=True).strip(),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check CookieGuard 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 cookieguard -- npx -y @aiscihub/cookieguard-mcp
{
"mcpServers": {
"cookieguard": {
"command": "npx",
"args": [
"-y",
"@aiscihub/cookieguard-mcp"
]
}
}
}
[mcp_servers.cookieguard]
command = "npx"
args = ["-y", "@aiscihub/cookieguard-mcp"]
{
"mcpServers": {
"cookieguard": {
"command": "npx",
"args": [
"-y",
"@aiscihub/cookieguard-mcp"
]
}
}
}
{
"servers": {
"cookieguard": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@aiscihub/cookieguard-mcp"
]
}
}
}
Check seven declared HTTP security header families without returning raw values
Count secret-like patterns in bounded local files without returning values, keys, paths,...
Fix GuardBee AI Security Engineer findings in your repo with your coding agent, then verify
Security reviews for coding agents: diffs checked against your org policy and live infrastructure.
Ask about your Kodem Security data and act on findings in plain language, with your permissions.
Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Argues against a security finding or a draft bug bounty report before you submit it.
Answers built from our own checks of this server.