WARDEN — MCP Security Firewall runs on your own machine — the client starts it, so there is no endpoint to ping. 1 318 installs a week from npm. Last commit 2 Nov 2026.
MCP security firewall: stdio wrap proxy or inspection tools; zero runtime dependencies.
We read the source, 22 h 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.
const child = spawn(ref.command, ref.args ?? [], {
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 warden -- npx -y @aimarket/warden
{
"mcpServers": {
"warden": {
"command": "npx",
"args": [
"-y",
"@aimarket/warden"
]
}
}
}
[mcp_servers.warden]
command = "npx"
args = ["-y", "@aimarket/warden"]
{
"mcpServers": {
"warden": {
"command": "npx",
"args": [
"-y",
"@aimarket/warden"
]
}
}
}
{
"servers": {
"warden": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@aimarket/warden"
]
}
}
}
Real-time MCP & A2A prompt-injection, jailbreak, and tool-schema poisoning firewall for AI agents.
Security scanner and runtime proxy for MCP servers.
Real-time semantic security for AI coding agents and MCP tools
MCP runtime security proxy. Blocks dangerous AI agent tool calls with a policy engine.
AI security firewall & DLP proxy protecting API keys and blocking destructive commands.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Runtime proxy for MCP security, cost governance & audit
Reliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.
Answers built from our own checks of this server.