AI agents call suggest_refactoring to retrieve information from CodeGraphMCPServer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes code to identify refactoring opportunities, returning suggestions to the user. It does not modify, execute, delete, or commit any changes to the codebase. The output is purely informational analysis, making it a Read category tool with low severity—misuse would only result in suboptimal or incorrect refactoring suggestions, not data loss or code execution.
From the tool's definition The tool 'suggest_refactoring' with description 'Suggest refactoring opportunities' performs analysis and provides suggestions without executing changes or modifying code.
Documented attack patterns abuse exactly the kind of access suggest_refactoring gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CodeGraphMCPServer, and nothing reaches the server without passing your rules. This is the rule we recommend for suggest_refactoring:
{
"version": "1",
"default": "deny",
"tools": {
"suggest_refactoring": {}
}
}suggest_refactoring 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.
Suggest refactoring opportunities. It is categorised as a Read tool in the CodeGraphMCPServer MCP Server, which means it retrieves data without modifying state.
Register the CodeGraphMCPServer MCP server in PolicyLayer and add a rule for suggest_refactoring: 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 CodeGraphMCPServer. Nothing to install.
suggest_refactoring 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 suggest_refactoring 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 suggest_refactoring. 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.
suggest_refactoring is provided by the CodeGraphMCPServer MCP server (nahisaho/codegraphmcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CodeGraphMCPServer, 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.
14 CodeGraphMCPServer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.