WARDEN — MCP Security Firewall runs on your own machine — the client starts it, so there is no endpoint to ping. 61 installs a week from npm. Last commit 5 Sep 2026.
MCP security firewall: vet tool definitions before they reach the model.
Today is the operative word: we check WARDEN — MCP Security Firewall 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 warden -- npx -y @aimarket/warden
{
"mcpServers": {
"warden": {
"args": [
"-y",
"@aimarket/warden"
],
"command": "npx"
}
}
}
[mcp_servers.warden]
command = "npx"
args = ["-y", "@aimarket/warden"]
{
"mcpServers": {
"warden": {
"args": [
"-y",
"@aimarket/warden"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"warden": {
"args": [
"-y",
"@aimarket/warden"
],
"command": "npx"
}
}
}
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
MCP proxy adding security scanning, behavioral profiling, risk gating, and safe tool call execution.
Scan any MCP server for tool-poisoning, security, auth & license. Trust score before install.
MCP security trust-check for agents before installing MCPs, Skills or tools.
Free, read-only security scanner for remote MCP servers, before you connect them.
Security-first, self-hosted MCP server for Firefly III — 152 operations behind 5 scoped tools.
Security scanner for MCP servers and skill files. Detects AVE vulnerabilities before production.
Answers built from our own checks of this server.