Security Engineer runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 6 Nov 2026.
Fix GuardBee AI Security Engineer findings in your repo with your coding agent, then verify
Today is the operative word: we check Security Engineer 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 security-engineer -e 'GUARDBEE_API_KEY=<GUARDBEE_API_KEY>' -- npx -y @guardbee/mcp-security-engineer
{
"mcpServers": {
"security-engineer": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-security-engineer"
],
"env": {
"GUARDBEE_API_KEY": "<GUARDBEE_API_KEY>"
}
}
}
}
[mcp_servers.security-engineer]
command = "npx"
args = ["-y", "@guardbee/mcp-security-engineer"]
env = { GUARDBEE_API_KEY = "<GUARDBEE_API_KEY>" }
{
"mcpServers": {
"security-engineer": {
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-security-engineer"
],
"env": {
"GUARDBEE_API_KEY": "<GUARDBEE_API_KEY>"
}
}
}
}
{
"servers": {
"security-engineer": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@guardbee/mcp-security-engineer"
],
"env": {
"GUARDBEE_API_KEY": "<GUARDBEE_API_KEY>"
}
}
}
}
Put your own value in place of
<GUARDBEE_API_KEY> (GuardBee API key with remediations.read and remediations.write scopes).
The author’s registry entry marks it as required.
The repo guardian AI agents handshake with before they touch your code.
Scan a GitHub repository for vulnerabilities, with proof for every finding, from your coding agent.
Scores your code across 12 areas, with findings, fix prompts, and re-assessment in your AI agent
Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent
Abnormal Security email threats, cases, and reporting in your terminal and your AI agents.
Read your Proofie report on AI visibility and AI agents, and fix each finding on your site.
Audit repos for security, code quality and AI code risks; read findings and open fix PRs.
WingFoil — the repo-native intent layer for AI-native software engineering
Answers built from our own checks of this server.