Get all current test cases to see what requirements the regex pattern needs to satisfy.
AI agents call get_test_cases to retrieve information from MCPGex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns test case data without creating, modifying, or deleting anything. It provides visibility into regex pattern requirements, which is a standard Read operation. The low severity reflects that retrieving test metadata poses minimal risk to systems or workflows.
From the tool's definition The tool retrieves existing test cases via 'Get all current test cases' - a query operation with no modifications or side effects.
Documented attack patterns abuse exactly the kind of access get_test_cases 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 get_test_cases:
{
"version": "1",
"default": "deny",
"tools": {
"get_test_cases": {}
}
}get_test_cases is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get all current test cases to see what requirements the regex pattern needs to satisfy. It is categorised as a Read tool in the MCPGex MCP Server, which means it retrieves data without modifying state.
Register the MCPGex MCP server in PolicyLayer and add a rule for get_test_cases: 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.
get_test_cases is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_test_cases 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 get_test_cases. 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.
get_test_cases 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.