Test a regex pattern against all current test cases to see if it satisfies the requirements.
AI agents invoke test_regex to trigger actions in MCPGex. 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.
This tool executes a regex pattern evaluation against test cases, which constitutes running/executing code (pattern matching logic). While relatively benign in scope, it actively runs computational logic rather than simply reading static data. The blast radius is low since it only tests regex patterns and does not modify, delete, or interact with external systems.
From the tool's definition "Test a regex pattern against all current test cases" - the tool runs/executes a regex pattern against stored test cases
Documented attack patterns abuse exactly the kind of access test_regex gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCPGex, and nothing reaches the server without passing your rules. This is the rule we recommend for test_regex:
{
"version": "1",
"default": "deny",
"tools": {
"test_regex": {
"limits": [
{
"counter": "test_regex_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}test_regex 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.
Test a regex pattern against all current test cases to see if it satisfies the requirements. It is categorised as a Execute tool in the MCPGex MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCPGex MCP server in PolicyLayer and add a rule for test_regex: 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 MCPGex. Nothing to install.
test_regex 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_regex 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_regex. 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_regex is provided by the MCPGex MCP server (patzedi/mcpgex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCPGex, 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.
4 MCPGex tools catalogued and risk-classified — across an index of 43,000+ MCP servers.