Agent Security runs on your own machine — the client starts it, so there is no endpoint to ping. 61 installs a week from npm. Last commit 24 Apr 2026.
Security scanning and threat detection for AI agents
Nothing serious here today
Today is the operative word: we check Agent Security every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 agent-security -- npx -y agent-security-mcp{
"mcpServers": {
"agent-security": {
"command": "npx",
"args": [
"-y",
"agent-security-mcp"
]
}
}
}[mcp_servers.agent-security]
command = "npx"
args = ["-y", "agent-security-mcp"]{
"mcpServers": {
"agent-security": {
"command": "npx",
"args": [
"-y",
"agent-security-mcp"
]
}
}
}{
"servers": {
"agent-security": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agent-security-mcp"
]
}
}
}Alternatives to Agent Security
same job, measured the same wayAI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Security scanning and trust verification for AI agent tools.
Security scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.
Security scanner for MCP servers - detects tool poisoning and injection
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
MCP server for Abnormal Security — AI-powered email threat detection, cases, and remediation.
Agent Security — questions
Answers built from our own checks of this server.