MCP Audit Server runs on your own machine — the client starts it, so there is no endpoint to ping. 66 installs a week from npm. Last commit 24 Aug 2026.
Thin MCP and CLI proxy for AI agent and MCP security auditing via a hosted backend
Today is the operative word: we check MCP Audit Server 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 mcp-audit-server -e 'AGENT_SECURITY_API_KEY=<AGENT_SECURITY_API_KEY>' -- npx -y ledd-mcp-audit-server
{
"mcpServers": {
"mcp-audit-server": {
"command": "npx",
"args": [
"-y",
"ledd-mcp-audit-server"
],
"env": {
"AGENT_SECURITY_API_KEY": "<AGENT_SECURITY_API_KEY>"
}
}
}
}
[mcp_servers.mcp-audit-server]
command = "npx"
args = ["-y", "ledd-mcp-audit-server"]
env = { AGENT_SECURITY_API_KEY = "<AGENT_SECURITY_API_KEY>" }
{
"mcpServers": {
"mcp-audit-server": {
"command": "npx",
"args": [
"-y",
"ledd-mcp-audit-server"
],
"env": {
"AGENT_SECURITY_API_KEY": "<AGENT_SECURITY_API_KEY>"
}
}
}
}
{
"servers": {
"mcp-audit-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ledd-mcp-audit-server"
],
"env": {
"AGENT_SECURITY_API_KEY": "<AGENT_SECURITY_API_KEY>"
}
}
}
}
Put your own value in place of
<AGENT_SECURITY_API_KEY> (API key for the managed hosted audit backend).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
AGENT_SECURITY_BASE_URL (Optional HTTPS API origin for self-hosted or private deployments).
Real-time semantic security for AI coding agents and MCP tools
Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.
Runtime proxy for MCP security, cost governance & audit
Network, DNS, mail-auth and MCP endpoint security checks for AI agents, backed by adminkit.net.
Reliability + security proxy for MCP: runtime tool-security and a compliance-mapped audit trail.
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
A dead-simple, self-hosted MCP server for securely querying databases via AI agents.
Scans code, IaC and AI-agent config for security problems. Read-only — nothing can be edited.
Answers built from our own checks of this server.