Find code patterns that may be difficult to test (private methods, static methods, etc.)
AI agents call find_untestable_code to retrieve information from CodeRAG without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a static analysis tool that reads code structure and identifies patterns. It does not modify data, execute code, delete resources, or trigger external operations. The query-like nature (identifying difficult-to-test patterns) fits the Read category. Severity is low because misuse would only result in incorrect or incomplete code analysis reports, with no side effects on the actual codebase or systems.
From the tool's definition Tool performs analysis and discovery of code patterns ('find untestable code') with no modification, deletion, or execution capabilities. It retrieves and queries codebase information to identify testing challenges.
Documented attack patterns abuse exactly the kind of access find_untestable_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeRAG, and nothing reaches the server without passing your rules. This is the rule we recommend for find_untestable_code:
{
"version": "1",
"default": "deny",
"tools": {
"find_untestable_code": {}
}
}find_untestable_code 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.
Find code patterns that may be difficult to test (private methods, static methods, etc.). It is categorised as a Read tool in the CodeRAG MCP Server, which means it retrieves data without modifying state.
Register the CodeRAG MCP server in PolicyLayer and add a rule for find_untestable_code: 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 CodeRAG. Nothing to install.
find_untestable_code 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 find_untestable_code 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 find_untestable_code. 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.
find_untestable_code is provided by the CodeRAG MCP server (jonnoc/coderag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeRAG, 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.
38 CodeRAG tools catalogued and risk-classified — across an index of 43,000+ MCP servers.