AI agents invoke test_security to trigger actions in Better Auth MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool actively runs security tests against an authentication system, which constitutes execution of code/operations against live infrastructure. Security testing can trigger authentication flows, probe endpoints, and interact with real systems. Misuse or misdirection could expose vulnerabilities, trigger lockouts, or interfere with production auth systems, warranting a high severity rating.
From the tool's definition "Run security tests" — actively executes test routines against an authentication setup
Documented attack patterns abuse exactly the kind of access test_security gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Better Auth MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for test_security:
{
"version": "1",
"default": "deny",
"tools": {
"test_security": {
"limits": [
{
"counter": "test_security_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}test_security stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run security tests on Better-Auth setup. It is categorised as a Execute tool in the Better Auth MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Better Auth MCP Server MCP server in PolicyLayer and add a rule for test_security: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Better Auth MCP Server. Nothing to install.
test_security is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the test_security rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for test_security. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
test_security is provided by the Better Auth MCP Server MCP server (jamesjohnsdev/better-auth-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Better Auth MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Better Auth MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.