Agent Verify runs on your own machine — the client starts it, so there is no endpoint to ping. 151 installs a week from npm. Last commit 3 Nov 2026.
Security checks for AI agents and MCP configs: 124 tested checks, from your AI coding assistant.
Nothing serious here today
Today is the operative word: we check Agent Verify 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 agentverify -e 'AGENTVERIFY_API_KEY=<AGENTVERIFY_API_KEY>' -- npx -y agentverify{
"mcpServers": {
"agentverify": {
"command": "npx",
"args": [
"-y",
"agentverify"
],
"env": {
"AGENTVERIFY_API_KEY": "<AGENTVERIFY_API_KEY>"
}
}
}
}[mcp_servers.agentverify]
command = "npx"
args = ["-y", "agentverify"]
env = { AGENTVERIFY_API_KEY = "<AGENTVERIFY_API_KEY>" }{
"mcpServers": {
"agentverify": {
"command": "npx",
"args": [
"-y",
"agentverify"
],
"env": {
"AGENTVERIFY_API_KEY": "<AGENTVERIFY_API_KEY>"
}
}
}
}{
"servers": {
"agentverify": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agentverify"
],
"env": {
"AGENTVERIFY_API_KEY": "<AGENTVERIFY_API_KEY>"
}
}
}
}Put your own value in place of
<AGENTVERIFY_API_KEY> (Your Agent Verify API key (dashboard → API / CLI). Free accounts work).
The author’s registry entry marks it as required.
Alternatives to Agent Verify
same job, measured the same wayControl your Tesla from your AI assistant - climate, charging, access, and security.
Test your AI agents for security and safety weaknesses, and re-verify the fixes.
VaultGuard MCP Server - Yearn V3 / DeFi vault security and analysis tools for AI coding agents....
Read your EyalSec security events, machines, runs and rules from an AI assistant.
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
Real-time semantic security for AI coding agents and MCP tools
Agentic SDLC governance and security controls for AI coding agents working with GitHub.
Offline, rule-based security checks for your repo, dependencies, AI agent config and local app.
Agent Verify — questions
Answers built from our own checks of this server.