Search for files inside the VM (using grep)
AI agents call search_files to retrieve information from Virtualbox MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation using grep to query files within a VM. It retrieves and returns data without creating, modifying, deleting, or executing operations. It has minimal blast radius if misused by an AI agent - it can only discover information that already exists. The severity is low because file search operations do not alter VM state or data.
From the tool's definition Tool description explicitly states "Search for files inside the VM (using grep)" - grep is a read-only search utility that does not modify files or system state.
Attacks that exploit this kind of access
Search for files inside the VM (using grep). It is categorised as a Read tool in the Virtualbox MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Virtualbox MCP Server MCP server in PolicyLayer and add a rule for search_files: 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 Virtualbox MCP Server. Nothing to install.
search_files 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 search_files 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 search_files. 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.
search_files is provided by the Virtualbox MCP Server MCP server (usemanusai/virtualbox-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 →