Two-Key runs on your own machine — the client starts it, so there is no endpoint to ping. 635 installs a week from pypi. Last commit 28 Oct 2026.
Authorization proxy for another MCP server: a rule check and AI judges approve each tool call
We read the source, 2 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.
done = subprocess.run(["/bin/ps", "-o", "ruid=", "-p", str(ppid)], # nosec B603 - fixed argv, no shell
return yaml.load(text, Loader=loader) # nosec B506
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 two-key -- uvx two-key
{
"mcpServers": {
"two-key": {
"command": "uvx",
"args": [
"two-key"
]
}
}
}
[mcp_servers.two-key]
command = "uvx"
args = ["two-key"]
{
"mcpServers": {
"two-key": {
"command": "uvx",
"args": [
"two-key"
]
}
}
}
{
"servers": {
"two-key": {
"type": "stdio",
"command": "uvx",
"args": [
"two-key"
]
}
}
}
Authorization-gated MCP server to discover and run 670+ security tools for CTF, pentest, and DFIR.
Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call
Puts an MCP tool server behind Archytan Lite: each tool call is authorized and spent before it runs.
MCP Server for ThoughtSpot - provides OAuth authentication and tools for querying data
Policy proxy for MCP tool calls. A denied call never reaches the downstream server.
Transparent audit proxy for MCP servers: logs every tool call, flags poisoning and rug pulls.
Shared memory for connected AI tools. Projects, rules and skills over MCP. OAuth or API key.
Read, write and run Odoo actions from any AI app, as each user, with approval rules per colleague.
Answers built from our own checks of this server.