AI agents call find_refactors to retrieve information from VibeServe 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 metrics and patterns to suggest refactoring opportunities. It has no side effects: it does not execute code, modify files, delete anything, or trigger external operations. It is a read-only diagnostic tool that queries repository structure and code characteristics.
From the tool's definition Tool 'find_refactors' is described as finding or identifying refactor candidates (large files, duplicated symbols, dead code hints) — purely a search/analysis function with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Find refactor candidates: large files, duplicated symbols, dead code hints. It is categorised as a Read tool in the VibeServe MCP Server, which means it retrieves data without modifying state.
Register the VibeServe MCP server in PolicyLayer and add a rule for find_refactors: 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 VibeServe. Nothing to install.
find_refactors 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_refactors 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_refactors. 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_refactors is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →