MCP Seatbelt runs on your own machine — the client starts it, so there is no endpoint to ping. 86 installs a week from npm. Last commit 4 Aug 2026.
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
We read the source, 11 h ago · rules 3dff92dd89df
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.
пакет @kryptosai/mcp-seatbelt ссылается на anomalyco/mcp-seatbelt
this.child = spawn(this.command, this.args, {
Object.entries(process.env).filter(([, v]) => v !== undefined),
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-seatbelt -- npx -y @kryptosai/mcp-seatbelt
{
"mcpServers": {
"mcp-seatbelt": {
"args": [
"-y",
"@kryptosai/mcp-seatbelt"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-seatbelt]
command = "npx"
args = ["-y", "@kryptosai/mcp-seatbelt"]
{
"mcpServers": {
"mcp-seatbelt": {
"args": [
"-y",
"@kryptosai/mcp-seatbelt"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-seatbelt": {
"args": [
"-y",
"@kryptosai/mcp-seatbelt"
],
"command": "npx"
}
}
}
MCP gateway with runtime security policy, tool-call-level control, and audit of agent actions.
Real-time semantic security for AI coding agents and MCP tools
Runtime security for AI agent commerce. CLI + MCP server blocks hallucinated purchases.
Security proxy that wraps MCP servers with real-time monitoring and policy enforcement
Security proxy that automatically wraps MCP servers with real-time monitoring and policy enforcement
Zero-trust MCP security proxy with policy enforcement, PII scrubbing, approvals, and audit trails.
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
iptables for MCP — blocks dangerous tool calls, scans for secrets, logs everything.
Answers built from our own checks of this server.