mcpcut runs on your own machine — the client starts it, so there is no endpoint to ping. 592 installs a week from npm. Last commit 10 Oct 2026.
Journals every MCP tool call with secrets redacted; with a policy, holds risky calls for approval
What the code does
We read the source, 6 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.
return spawn(command, [...args], { stdio: 'inherit' })
const stats = await lstat(path.join(folder, name), { bigint: true })
export const DEFAULT_DOCKER_SOCKET = '/var/run/docker.sock'
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 mcpcut -- npx -y mcpcut{
"mcpServers": {
"mcpcut": {
"args": [
"-y",
"mcpcut"
],
"command": "npx"
}
}
}[mcp_servers.mcpcut]
command = "npx"
args = ["-y", "mcpcut"]{
"mcpServers": {
"mcpcut": {
"args": [
"-y",
"mcpcut"
],
"command": "npx"
}
}
}{
"mcpServers": {
"mcpcut": {
"args": [
"-y",
"mcpcut"
],
"command": "npx"
}
}
}Alternatives to mcpcut
same job, measured the same wayCordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
Credential isolation for AI agents: placeholder secrets, policy checks, optional human approval.
iptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.
Secure MCP SSH automation server with policy controls, resources, prompts, stdio, and HTTP.
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Zero-Trust PII & secrets sanitizer for AI agents with in-memory local redaction.
Scans AI coding sessions and assistant configs for leaked secrets and risky hooks; local, redacted
mcpcut — questions
Answers built from our own checks of this server.