suggest_folder_structure
AI agents call suggest_folder_structure to retrieve information from Code Review without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name alone, 'suggest_folder_structure' most likely analyzes existing code and suggests (reads/recommends) a folder organization without making changes. The server context (code review, quality checks, refactoring suggestions) supports a read/advisory role. However, the empty description lowers confidence significantly, as the tool could potentially write or restructure files.
From the tool's definition Tool name: suggest_folder_structure; description is empty and uninformative.
Attacks that exploit this kind of access
suggest_folder_structure. It is categorised as a Read tool in the Code Review MCP Server, which means it retrieves data without modifying state.
Register the Code Review MCP server in PolicyLayer and add a rule for suggest_folder_structure: 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 Code Review. Nothing to install.
suggest_folder_structure 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_folder_structure 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_folder_structure. 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_folder_structure is provided by the Code Review MCP server (troshenkov/code-review-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →