Find architectural issues (circular dependencies, god classes, high coupling)
AI agents call find_architectural_issues 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 tool retrieves and reports on code structure analysis metrics stored in the Neo4j knowledge graph. While it provides insights into code quality problems, it performs no write operations, does not execute code, and does not delete or modify data. It is purely an informational query operation with no side effects on the codebase or external systems.
From the tool's definition Tool description states it 'Find[s] architectural issues' - a querying/analysis operation on the knowledge graph.
Documented attack patterns abuse exactly the kind of access find_architectural_issues 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_architectural_issues:
{
"version": "1",
"default": "deny",
"tools": {
"find_architectural_issues": {}
}
}find_architectural_issues 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 architectural issues (circular dependencies, god classes, high coupling). 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_architectural_issues: 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_architectural_issues 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_architectural_issues 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_architectural_issues. 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_architectural_issues 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.